~bzr-pqm/bzr/bzr.dev

4763.2.4 by John Arbash Meinel
merge bzr.2.1 in preparation for NEWS entry.
1
# Copyright (C) 2008, 2009, 2010 Canonical Ltd
3641.3.1 by John Arbash Meinel
Bring in the btree_index and chunk_writer code and their tests.
2
#
3
# This program is free software; you can redistribute it and/or modify
3641.3.29 by John Arbash Meinel
Cleanup the copyright headers
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.
3641.3.1 by John Arbash Meinel
Bring in the btree_index and chunk_writer code and their tests.
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
4183.7.1 by Sabin Iacob
update FSF mailing address
15
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
3641.3.1 by John Arbash Meinel
Bring in the btree_index and chunk_writer code and their tests.
16
#
17
6379.6.7 by Jelmer Vernooij
Move importing from future until after doc string, otherwise the doc string will disappear.
18
"""B+Tree index parsing."""
19
6379.6.1 by Jelmer Vernooij
Import absolute_import in a few places.
20
from __future__ import absolute_import
21
4789.28.1 by John Arbash Meinel
Use StaticTuple as part of the builder process.
22
from bzrlib import static_tuple
23
24
3641.3.1 by John Arbash Meinel
Bring in the btree_index and chunk_writer code and their tests.
25
def _parse_leaf_lines(bytes, key_length, ref_list_length):
26
    lines = bytes.split('\n')
27
    nodes = []
4789.28.1 by John Arbash Meinel
Use StaticTuple as part of the builder process.
28
    as_st = static_tuple.StaticTuple.from_sequence
29
    stuple = static_tuple.StaticTuple
3641.3.1 by John Arbash Meinel
Bring in the btree_index and chunk_writer code and their tests.
30
    for line in lines[1:]:
31
        if line == '':
32
            return nodes
33
        elements = line.split('\0', key_length)
34
        # keys are tuples
4789.28.1 by John Arbash Meinel
Use StaticTuple as part of the builder process.
35
        key = as_st(elements[:key_length]).intern()
3641.3.1 by John Arbash Meinel
Bring in the btree_index and chunk_writer code and their tests.
36
        line = elements[-1]
37
        references, value = line.rsplit('\0', 1)
38
        if ref_list_length:
39
            ref_lists = []
40
            for ref_string in references.split('\t'):
4789.28.1 by John Arbash Meinel
Use StaticTuple as part of the builder process.
41
                ref_list = as_st([as_st(ref.split('\0')).intern()
42
                                  for ref in ref_string.split('\r') if ref])
43
                ref_lists.append(ref_list)
44
            ref_lists = as_st(ref_lists)
45
            node_value = stuple(value, ref_lists)
3641.3.1 by John Arbash Meinel
Bring in the btree_index and chunk_writer code and their tests.
46
        else:
4789.28.1 by John Arbash Meinel
Use StaticTuple as part of the builder process.
47
            node_value = stuple(value, stuple())
48
        # No need for StaticTuple here as it is put into a dict
3641.3.1 by John Arbash Meinel
Bring in the btree_index and chunk_writer code and their tests.
49
        nodes.append((key, node_value))
50
    return nodes
3641.3.18 by John Arbash Meinel
Start working on a compiled function for transforming
51
52
53
def _flatten_node(node, reference_lists):
54
    """Convert a node into the serialized form.
55
56
    :param node: A tuple representing a node (key_tuple, value, references)
57
    :param reference_lists: Does this index have reference lists?
58
    :return: (string_key, flattened)
59
        string_key  The serialized key for referencing this node
60
        flattened   A string with the serialized form for the contents
61
    """
62
    if reference_lists:
63
        # TODO: Consider turning this back into the 'unoptimized' nested loop
64
        #       form. It is probably more obvious for most people, and this is
65
        #       just a reference implementation.
66
        flattened_references = ['\r'.join(['\x00'.join(reference)
67
                                           for reference in ref_list])
68
                                for ref_list in node[3]]
69
    else:
70
        flattened_references = []
71
    string_key = '\x00'.join(node[1])
72
    line = ("%s\x00%s\x00%s\n" % (string_key,
73
        '\t'.join(flattened_references), node[2]))
74
    return string_key, line