Mercurial > public > mercurial-scm > hg
annotate mercurial/revlogutils/nodemap.py @ 44312:563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
When we write new full files, it replace an older one with a different name. We
add the associated cleanup for the older file to be removed after the
transaction.
We delete all file matching the expected pattern to give use extra chance to
delete orphan files we might have failed to delete earlier.
Note: eventually we won't rewrite all data for each transaction. This is coming
in later changesets.
Differential Revision: https://phab.mercurial-scm.org/D7839
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Wed, 15 Jan 2020 15:47:59 +0100 |
parents | 2b72c4ff8ed1 |
children | 7f4f7ef3133e |
rev | line source |
---|---|
44034
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
1 # nodemap.py - nodemap related code and utilities |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
2 # |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
3 # Copyright 2019 Pierre-Yves David <pierre-yves.david@octobus.net> |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
4 # Copyright 2019 George Racinet <georges.racinet@octobus.net> |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
5 # |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
6 # This software may be used and distributed according to the terms of the |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
7 # GNU General Public License version 2 or any later version. |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
8 |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
9 from __future__ import absolute_import |
44307
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
10 |
44311
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
11 import os |
44312
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
12 import re |
44307
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
13 import struct |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
14 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
15 from .. import ( |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
16 error, |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
17 node as nodemod, |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
18 pycompat, |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
19 ) |
44034
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
20 |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
21 |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
22 class NodeMap(dict): |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
23 def __missing__(self, x): |
ab595920de0e
revlogutils: move the NodeMap class in a dedicated nodemap module
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
diff
changeset
|
24 raise error.RevlogError(b'unknown node: %s' % x) |
44307
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
25 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
26 |
44309
6c07480d6659
nodemap: add a function to read the data from disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44308
diff
changeset
|
27 def persisted_data(revlog): |
6c07480d6659
nodemap: add a function to read the data from disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44308
diff
changeset
|
28 """read the nodemap for a revlog from disk""" |
6c07480d6659
nodemap: add a function to read the data from disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44308
diff
changeset
|
29 if revlog.nodemap_file is None: |
6c07480d6659
nodemap: add a function to read the data from disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44308
diff
changeset
|
30 return None |
44311
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
31 pdata = revlog.opener.tryread(revlog.nodemap_file) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
32 if not pdata: |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
33 return None |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
34 offset = 0 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
35 (version,) = S_VERSION.unpack(pdata[offset : offset + S_VERSION.size]) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
36 if version != ONDISK_VERSION: |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
37 return None |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
38 offset += S_VERSION.size |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
39 (uuid_size,) = S_HEADER.unpack(pdata[offset : offset + S_HEADER.size]) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
40 offset += S_HEADER.size |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
41 uid = pdata[offset : offset + uuid_size] |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
42 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
43 filename = _rawdata_filepath(revlog, uid) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
44 return revlog.opener.tryread(filename) |
44309
6c07480d6659
nodemap: add a function to read the data from disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44308
diff
changeset
|
45 |
6c07480d6659
nodemap: add a function to read the data from disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44308
diff
changeset
|
46 |
44308
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
47 def setup_persistent_nodemap(tr, revlog): |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
48 """Install whatever is needed transaction side to persist a nodemap on disk |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
49 |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
50 (only actually persist the nodemap if this is relevant for this revlog) |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
51 """ |
44310
daad3aace942
nodemap: only use persistent nodemap for non-inlined revlog
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44309
diff
changeset
|
52 if revlog._inline: |
daad3aace942
nodemap: only use persistent nodemap for non-inlined revlog
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44309
diff
changeset
|
53 return # inlined revlog are too small for this to be relevant |
44308
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
54 if revlog.nodemap_file is None: |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
55 return # we do not use persistent_nodemap on this revlog |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
56 callback_id = b"revlog-persistent-nodemap-%s" % revlog.nodemap_file |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
57 if tr.hasfinalize(callback_id): |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
58 return # no need to register again |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
59 tr.addfinalize(callback_id, lambda tr: _persist_nodemap(tr, revlog)) |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
60 |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
61 |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
62 def _persist_nodemap(tr, revlog): |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
63 """Write nodemap data on disk for a given revlog |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
64 """ |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
65 if getattr(revlog, 'filteredrevs', ()): |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
66 raise error.ProgrammingError( |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
67 "cannot persist nodemap of a filtered changelog" |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
68 ) |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
69 if revlog.nodemap_file is None: |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
70 msg = "calling persist nodemap on a revlog without the feature enableb" |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
71 raise error.ProgrammingError(msg) |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
72 data = persistent_data(revlog.index) |
44311
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
73 uid = _make_uid() |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
74 datafile = _rawdata_filepath(revlog, uid) |
44312
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
75 olds = _other_rawdata_filepath(revlog, uid) |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
76 if olds: |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
77 realvfs = getattr(revlog, '_realopener', revlog.opener) |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
78 |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
79 def cleanup(tr): |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
80 for oldfile in olds: |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
81 realvfs.tryunlink(oldfile) |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
82 |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
83 callback_id = b"revlog-cleanup-nodemap-%s" % revlog.nodemap_file |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
84 tr.addpostclose(callback_id, cleanup) |
44311
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
85 # EXP-TODO: if this is a cache, this should use a cache vfs, not a |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
86 # store vfs |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
87 with revlog.opener(datafile, b'w') as fd: |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
88 fd.write(data) |
44308
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
89 # EXP-TODO: if this is a cache, this should use a cache vfs, not a |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
90 # store vfs |
44311
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
91 with revlog.opener(revlog.nodemap_file, b'w', atomictemp=True) as fp: |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
92 fp.write(_serialize_docket(uid)) |
44308
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
93 # EXP-TODO: if the transaction abort, we should remove the new data and |
44311
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
94 # reinstall the old one. |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
95 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
96 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
97 ### Nodemap docket file |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
98 # |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
99 # The nodemap data are stored on disk using 2 files: |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
100 # |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
101 # * a raw data files containing a persistent nodemap |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
102 # (see `Nodemap Trie` section) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
103 # |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
104 # * a small "docket" file containing medatadata |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
105 # |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
106 # While the nodemap data can be multiple tens of megabytes, the "docket" is |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
107 # small, it is easy to update it automatically or to duplicated its content |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
108 # during a transaction. |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
109 # |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
110 # Multiple raw data can exist at the same time (The currently valid one and a |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
111 # new one beind used by an in progress transaction). To accomodate this, the |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
112 # filename hosting the raw data has a variable parts. The exact filename is |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
113 # specified inside the "docket" file. |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
114 # |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
115 # The docket file contains information to find, qualify and validate the raw |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
116 # data. Its content is currently very light, but it will expand as the on disk |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
117 # nodemap gains the necessary features to be used in production. |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
118 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
119 # version 0 is experimental, no BC garantee, do no use outside of tests. |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
120 ONDISK_VERSION = 0 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
121 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
122 S_VERSION = struct.Struct(">B") |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
123 S_HEADER = struct.Struct(">B") |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
124 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
125 ID_SIZE = 8 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
126 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
127 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
128 def _make_uid(): |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
129 """return a new unique identifier. |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
130 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
131 The identifier is random and composed of ascii characters.""" |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
132 return nodemod.hex(os.urandom(ID_SIZE)) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
133 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
134 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
135 def _serialize_docket(uid): |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
136 """return serialized bytes for a docket using the passed uid""" |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
137 data = [] |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
138 data.append(S_VERSION.pack(ONDISK_VERSION)) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
139 data.append(S_HEADER.pack(len(uid))) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
140 data.append(uid) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
141 return b''.join(data) |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
142 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
143 |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
144 def _rawdata_filepath(revlog, uid): |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
145 """The (vfs relative) nodemap's rawdata file for a given uid""" |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
146 prefix = revlog.nodemap_file[:-2] |
2b72c4ff8ed1
nodemap: use an intermediate "docket" file to carry small metadata
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44310
diff
changeset
|
147 return b"%s-%s.nd" % (prefix, uid) |
44308
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
148 |
5962fd0d1045
nodemap: write nodemap data on disk
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44307
diff
changeset
|
149 |
44312
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
150 def _other_rawdata_filepath(revlog, uid): |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
151 prefix = revlog.nodemap_file[:-2] |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
152 pattern = re.compile(b"(^|/)%s-[0-9a-f]+\.nd$" % prefix) |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
153 new_file_path = _rawdata_filepath(revlog, uid) |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
154 new_file_name = revlog.opener.basename(new_file_path) |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
155 dirpath = revlog.opener.dirname(new_file_path) |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
156 others = [] |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
157 for f in revlog.opener.listdir(dirpath): |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
158 if pattern.match(f) and f != new_file_name: |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
159 others.append(f) |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
160 return others |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
161 |
563dfdfd01a4
nodemap: delete older raw data file when creating a new ones
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44311
diff
changeset
|
162 |
44307
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
163 ### Nodemap Trie |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
164 # |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
165 # This is a simple reference implementation to compute and persist a nodemap |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
166 # trie. This reference implementation is write only. The python version of this |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
167 # is not expected to be actually used, since it wont provide performance |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
168 # improvement over existing non-persistent C implementation. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
169 # |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
170 # The nodemap is persisted as Trie using 4bits-address/16-entries block. each |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
171 # revision can be adressed using its node shortest prefix. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
172 # |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
173 # The trie is stored as a sequence of block. Each block contains 16 entries |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
174 # (signed 64bit integer, big endian). Each entry can be one of the following: |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
175 # |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
176 # * value >= 0 -> index of sub-block |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
177 # * value == -1 -> no value |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
178 # * value < -1 -> a revision value: rev = -(value+10) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
179 # |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
180 # The implementation focus on simplicity, not on performance. A Rust |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
181 # implementation should provide a efficient version of the same binary |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
182 # persistence. This reference python implementation is never meant to be |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
183 # extensively use in production. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
184 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
185 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
186 def persistent_data(index): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
187 """return the persistent binary form for a nodemap for a given index |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
188 """ |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
189 trie = _build_trie(index) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
190 return _persist_trie(trie) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
191 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
192 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
193 S_BLOCK = struct.Struct(">" + ("l" * 16)) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
194 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
195 NO_ENTRY = -1 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
196 # rev 0 need to be -2 because 0 is used by block, -1 is a special value. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
197 REV_OFFSET = 2 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
198 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
199 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
200 def _transform_rev(rev): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
201 """Return the number used to represent the rev in the tree. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
202 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
203 (or retrieve a rev number from such representation) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
204 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
205 Note that this is an involution, a function equal to its inverse (i.e. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
206 which gives the identity when applied to itself). |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
207 """ |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
208 return -(rev + REV_OFFSET) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
209 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
210 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
211 def _to_int(hex_digit): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
212 """turn an hexadecimal digit into a proper integer""" |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
213 return int(hex_digit, 16) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
214 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
215 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
216 def _build_trie(index): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
217 """build a nodemap trie |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
218 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
219 The nodemap stores revision number for each unique prefix. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
220 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
221 Each block is a dictionary with keys in `[0, 15]`. Values are either |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
222 another block or a revision number. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
223 """ |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
224 root = {} |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
225 for rev in range(len(index)): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
226 hex = nodemod.hex(index[rev][7]) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
227 _insert_into_block(index, 0, root, rev, hex) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
228 return root |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
229 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
230 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
231 def _insert_into_block(index, level, block, current_rev, current_hex): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
232 """insert a new revision in a block |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
233 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
234 index: the index we are adding revision for |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
235 level: the depth of the current block in the trie |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
236 block: the block currently being considered |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
237 current_rev: the revision number we are adding |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
238 current_hex: the hexadecimal representation of the of that revision |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
239 """ |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
240 hex_digit = _to_int(current_hex[level : level + 1]) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
241 entry = block.get(hex_digit) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
242 if entry is None: |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
243 # no entry, simply store the revision number |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
244 block[hex_digit] = current_rev |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
245 elif isinstance(entry, dict): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
246 # need to recurse to an underlying block |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
247 _insert_into_block(index, level + 1, entry, current_rev, current_hex) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
248 else: |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
249 # collision with a previously unique prefix, inserting new |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
250 # vertices to fit both entry. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
251 other_hex = nodemod.hex(index[entry][7]) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
252 other_rev = entry |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
253 new = {} |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
254 block[hex_digit] = new |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
255 _insert_into_block(index, level + 1, new, other_rev, other_hex) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
256 _insert_into_block(index, level + 1, new, current_rev, current_hex) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
257 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
258 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
259 def _persist_trie(root): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
260 """turn a nodemap trie into persistent binary data |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
261 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
262 See `_build_trie` for nodemap trie structure""" |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
263 block_map = {} |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
264 chunks = [] |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
265 for tn in _walk_trie(root): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
266 block_map[id(tn)] = len(chunks) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
267 chunks.append(_persist_block(tn, block_map)) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
268 return b''.join(chunks) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
269 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
270 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
271 def _walk_trie(block): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
272 """yield all the block in a trie |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
273 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
274 Children blocks are always yield before their parent block. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
275 """ |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
276 for (_, item) in sorted(block.items()): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
277 if isinstance(item, dict): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
278 for sub_block in _walk_trie(item): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
279 yield sub_block |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
280 yield block |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
281 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
282 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
283 def _persist_block(block_node, block_map): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
284 """produce persistent binary data for a single block |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
285 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
286 Children block are assumed to be already persisted and present in |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
287 block_map. |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
288 """ |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
289 data = tuple(_to_value(block_node.get(i), block_map) for i in range(16)) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
290 return S_BLOCK.pack(*data) |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
291 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
292 |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
293 def _to_value(item, block_map): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
294 """persist any value as an integer""" |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
295 if item is None: |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
296 return NO_ENTRY |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
297 elif isinstance(item, dict): |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
298 return block_map[id(item)] |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
299 else: |
c577bb4a04d4
nodemap: have some python code writing a nodemap in persistent binary form
Pierre-Yves David <pierre-yves.david@octobus.net>
parents:
44034
diff
changeset
|
300 return _transform_rev(item) |