~bzr-pqm/bzr/bzr.dev

4869.3.27 by Andrew Bennetts
Move news_merge plugin from contrib to bzrlib/plugins, change it to be enabled via a 'news_merge_files' config option, move more code out of the __init__ to minimise overhead, and add lots of docstrings, add NEWS entry.
1
# Copyright (C) 2010 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
"""Simple parser for bzr's NEWS file.
18
19
Simple as this is, it's a bit over-powered for news_merge's needs, which only
20
cares about 'bullet' and 'everything else'.
21
22
This module can be run as a standalone Python program; pass it a filename and
23
it will print the parsed form of a file (a series of 2-tuples, see
24
simple_parse's docstring).
25
"""
4869.4.1 by Andrew Bennetts
Add plugin for merging bzr's NEWS file to contrib/.
26
27
28
def simple_parse(content):
4869.3.27 by Andrew Bennetts
Move news_merge plugin from contrib to bzrlib/plugins, change it to be enabled via a 'news_merge_files' config option, move more code out of the __init__ to minimise overhead, and add lots of docstrings, add NEWS entry.
29
    """Returns blocks, where each block is a 2-tuple (kind, text).
30
    
31
    :kind: one of 'heading', 'release', 'section', 'empty' or 'text'.
32
    :text: a str, including newlines.
33
    """
4869.4.1 by Andrew Bennetts
Add plugin for merging bzr's NEWS file to contrib/.
34
    blocks = content.split('\n\n')
35
    for block in blocks:
36
        if block.startswith('###'):
37
            # First line is ###...: Top heading
38
            yield 'heading', block
39
            continue
40
        last_line = block.rsplit('\n', 1)[-1]
41
        if last_line.startswith('###'):
42
            # last line is ###...: 2nd-level heading
43
            yield 'release', block
44
        elif last_line.startswith('***'):
45
            # last line is ***...: 3rd-level heading
46
            yield 'section', block
47
        elif block.startswith('* '):
48
            # bullet
49
            yield 'bullet', block
50
        elif block.strip() == '':
51
            # empty
52
            yield 'empty', block
53
        else:
54
            # plain text
55
            yield 'text', block
56
57
58
if __name__ == '__main__':
59
    import sys
60
    content = open(sys.argv[1], 'rb').read()
61
    for result in simple_parse(content):
62
        print result