rdf-lmdb 0.2.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +13 -0
- data/.rspec +3 -0
- data/.travis.yml +7 -0
- data/Gemfile +7 -0
- data/LICENSE +202 -0
- data/README.md +67 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/rdf-lmdb.rb +1 -0
- data/lib/rdf/lmdb.rb +873 -0
- data/lib/rdf/lmdb/version.rb +5 -0
- data/rdf-lmdb.gemspec +40 -0
- metadata +156 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 44a37cfc92db953f40ab6973acdacd645d652f1b5cc0c4e2524727eadaddbe3a
|
4
|
+
data.tar.gz: 25fffce08cbe02ca7baeacd485bd1bf8124cd735344a6203b51c79bbcba7f33d
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 5efc6ee2af73f21d4e1810f176b4652b78517d396f7a13ff70680ad5042a4b43549f923845abf39e0b79193806d3ae10452e3f2aa090f577c796824d4a0ae2de
|
7
|
+
data.tar.gz: '08f9e412178177a143b513a9379606a4290f1fa89de0f74afed6dd9d6068d63813bc3ea8c032f373866f0b9d9a1b066b4366b50e39b549b0569716ed1356b666'
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,202 @@
|
|
1
|
+
|
2
|
+
Apache License
|
3
|
+
Version 2.0, January 2004
|
4
|
+
http://www.apache.org/licenses/
|
5
|
+
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
7
|
+
|
8
|
+
1. Definitions.
|
9
|
+
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
12
|
+
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
14
|
+
the copyright owner that is granting the License.
|
15
|
+
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
17
|
+
other entities that control, are controlled by, or are under common
|
18
|
+
control with that entity. For the purposes of this definition,
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
20
|
+
direction or management of such entity, whether by contract or
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
23
|
+
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
25
|
+
exercising permissions granted by this License.
|
26
|
+
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
28
|
+
including but not limited to software source code, documentation
|
29
|
+
source, and configuration files.
|
30
|
+
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
32
|
+
transformation or translation of a Source form, including but
|
33
|
+
not limited to compiled object code, generated documentation,
|
34
|
+
and conversions to other media types.
|
35
|
+
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
37
|
+
Object form, made available under the License, as indicated by a
|
38
|
+
copyright notice that is included in or attached to the work
|
39
|
+
(an example is provided in the Appendix below).
|
40
|
+
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
47
|
+
the Work and Derivative Works thereof.
|
48
|
+
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
50
|
+
the original version of the Work and any modifications or additions
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
52
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
62
|
+
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
64
|
+
on behalf of whom a Contribution has been received by Licensor and
|
65
|
+
subsequently incorporated within the Work.
|
66
|
+
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
73
|
+
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
79
|
+
where such license applies only to those patent claims licensable
|
80
|
+
by such Contributor that are necessarily infringed by their
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
83
|
+
institute patent litigation against any entity (including a
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
86
|
+
or contributory patent infringement, then any patent licenses
|
87
|
+
granted to You under this License for that Work shall terminate
|
88
|
+
as of the date such litigation is filed.
|
89
|
+
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
92
|
+
modifications, and in Source or Object form, provided that You
|
93
|
+
meet the following conditions:
|
94
|
+
|
95
|
+
(a) You must give any other recipients of the Work or
|
96
|
+
Derivative Works a copy of this License; and
|
97
|
+
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
99
|
+
stating that You changed the files; and
|
100
|
+
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
103
|
+
attribution notices from the Source form of the Work,
|
104
|
+
excluding those notices that do not pertain to any part of
|
105
|
+
the Derivative Works; and
|
106
|
+
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
109
|
+
include a readable copy of the attribution notices contained
|
110
|
+
within such NOTICE file, excluding those notices that do not
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
112
|
+
of the following places: within a NOTICE text file distributed
|
113
|
+
as part of the Derivative Works; within the Source form or
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
115
|
+
within a display generated by the Derivative Works, if and
|
116
|
+
wherever such third-party notices normally appear. The contents
|
117
|
+
of the NOTICE file are for informational purposes only and
|
118
|
+
do not modify the License. You may add Your own attribution
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
121
|
+
that such additional attribution notices cannot be construed
|
122
|
+
as modifying the License.
|
123
|
+
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
125
|
+
may provide additional or different license terms and conditions
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
129
|
+
the conditions stated in this License.
|
130
|
+
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
134
|
+
this License, without any additional terms or conditions.
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
136
|
+
the terms of any separate license agreement you may have executed
|
137
|
+
with Licensor regarding such Contributions.
|
138
|
+
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
141
|
+
except as required for reasonable and customary use in describing the
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
143
|
+
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
153
|
+
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
159
|
+
incidental, or consequential damages of any character arising as a
|
160
|
+
result of this License or out of the use or inability to use the
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
163
|
+
other commercial damages or losses), even if such Contributor
|
164
|
+
has been advised of the possibility of such damages.
|
165
|
+
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
169
|
+
or other liability obligations and/or rights consistent with this
|
170
|
+
License. However, in accepting such obligations, You may act only
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
175
|
+
of your accepting any such warranty or additional liability.
|
176
|
+
|
177
|
+
END OF TERMS AND CONDITIONS
|
178
|
+
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
180
|
+
|
181
|
+
To apply the Apache License to your work, attach the following
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
183
|
+
replaced with your own identifying information. (Don't include
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
185
|
+
comment syntax for the file format. We also recommend that a
|
186
|
+
file or class name and description of purpose be included on the
|
187
|
+
same "printed page" as the copyright notice for easier
|
188
|
+
identification within third-party archives.
|
189
|
+
|
190
|
+
Copyright [yyyy] [name of copyright owner]
|
191
|
+
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
193
|
+
you may not use this file except in compliance with the License.
|
194
|
+
You may obtain a copy of the License at
|
195
|
+
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
197
|
+
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
201
|
+
See the License for the specific language governing permissions and
|
202
|
+
limitations under the License.
|
data/README.md
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
# RDF::LMDB - Lightweight, persistent, transactional RDF store
|
2
|
+
|
3
|
+
This library implements `RDF::Repository` using the Symax Lightning
|
4
|
+
MDB key-value database. It is intended to be a basic, durable,
|
5
|
+
locally-attached quad store, that avails itself of the properties of
|
6
|
+
LMDB.
|
7
|
+
|
8
|
+
`RDF::LMDB` is _also_ intended to provide a reference implementation
|
9
|
+
of an architecture for storing RDF in _any_ key-value database, such
|
10
|
+
that this adapter could be ported, or indeed the data _imported_, to
|
11
|
+
other back-ends (e.g. Berkeley DB, LevelDB, Kyoto Cabinet…) without
|
12
|
+
having to significantly change the design. The only real requirement
|
13
|
+
for the back-end is some kind of cursor functionality, and the
|
14
|
+
handling of multi-valued keys.
|
15
|
+
|
16
|
+
## Architecture
|
17
|
+
|
18
|
+
The system uses binary SHA-256 digests of N-Triples representations of
|
19
|
+
terms and statements. Terms are normalized first before being hashed.
|
20
|
+
The hashes themselves are stored in their binary representation.
|
21
|
+
|
22
|
+
### Triples
|
23
|
+
|
24
|
+
The main content of the store is keyed on the hash of a normalized
|
25
|
+
N-Triples statement (including the terminating ` .`). Its values are
|
26
|
+
the concatenated hashes of the individual terms:
|
27
|
+
|
28
|
+
sha256(s <sp> p <sp> o " .") => sha256(s) sha256(p) sha256(o)
|
29
|
+
|
30
|
+
### GSPO
|
31
|
+
|
32
|
+
There are four indices that resolve terms to statements, _graph_,
|
33
|
+
_subject_, _predicate_, _object_, respectively:
|
34
|
+
|
35
|
+
sha256(term) => sha256(s <sp> p <sp> o " .")
|
36
|
+
|
37
|
+
### Node Resolution
|
38
|
+
|
39
|
+
Finally, there is an index that maps the digests of the terms back to
|
40
|
+
their normalized N-Triples representations:
|
41
|
+
|
42
|
+
sha256(term) => term
|
43
|
+
|
44
|
+
## API Documentation
|
45
|
+
|
46
|
+
Generated and deposited
|
47
|
+
[in the usual place](http://www.rubydoc.info/gems/rdf-lmdb/).
|
48
|
+
|
49
|
+
## Installation
|
50
|
+
|
51
|
+
Come on, you know how to do this:
|
52
|
+
|
53
|
+
$ gem install rdf-lmdb
|
54
|
+
|
55
|
+
Or, [download it off rubygems.org](https://rubygems.org/gems/rdf-lmdb).
|
56
|
+
|
57
|
+
## Contributing
|
58
|
+
|
59
|
+
Bug reports and pull requests are welcome at
|
60
|
+
[the GitHub repository](https://github.com/doriantaylor/rb-rdf-sak).
|
61
|
+
|
62
|
+
## Copyright & License
|
63
|
+
|
64
|
+
©2019 [Dorian Taylor](https://doriantaylor.com/)
|
65
|
+
|
66
|
+
This software is provided under
|
67
|
+
the [Apache License, 2.0](https://www.apache.org/licenses/LICENSE-2.0).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "rdf/lmdb"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/lib/rdf-lmdb.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'rdf/lmdb'
|
data/lib/rdf/lmdb.rb
ADDED
@@ -0,0 +1,873 @@
|
|
1
|
+
require 'rdf/lmdb/version'
|
2
|
+
|
3
|
+
require 'rdf'
|
4
|
+
require 'rdf/ntriples'
|
5
|
+
require 'pathname'
|
6
|
+
require 'lmdb'
|
7
|
+
require 'digest'
|
8
|
+
require 'unf' # lol unf unf unf
|
9
|
+
|
10
|
+
module RDF
|
11
|
+
|
12
|
+
class Node
|
13
|
+
|
14
|
+
private
|
15
|
+
|
16
|
+
B64_ALPHA = ((?A..?Z).to_a + (?a..?z).to_a + (?0..?9).to_a + %w(- _)).freeze
|
17
|
+
|
18
|
+
def make_cheapo_b64_uuid_ncname
|
19
|
+
vals = (1..20).map { rand 64 } # generate the content
|
20
|
+
vals.push(rand(4) + 8) # last digit is special
|
21
|
+
'E' + vals.map { |v| B64_ALPHA[v] }.join('') # 'E' for UUID v4
|
22
|
+
end
|
23
|
+
|
24
|
+
public
|
25
|
+
|
26
|
+
# Monkeypatch the bnode identifier generator because memory
|
27
|
+
# addresses have a tendency to be the same across runs on certain systems
|
28
|
+
def initialize(id = nil)
|
29
|
+
id = nil if id.to_s.empty?
|
30
|
+
@id = (id || make_cheapo_b64_uuid_ncname).to_s.freeze
|
31
|
+
end
|
32
|
+
|
33
|
+
end
|
34
|
+
|
35
|
+
module LMDB
|
36
|
+
|
37
|
+
# ???
|
38
|
+
class Transaction < ::RDF::Transaction
|
39
|
+
private
|
40
|
+
|
41
|
+
# LMDB transactions have to happen inside a block, while
|
42
|
+
# RDF::Transactable transactions can float freely.
|
43
|
+
|
44
|
+
def wrap_txn &block
|
45
|
+
begin
|
46
|
+
@repository.env.transaction !@mutable do |t|
|
47
|
+
@txn = t
|
48
|
+
|
49
|
+
case block.arity
|
50
|
+
when 1 then block.call(self)
|
51
|
+
else self.instance_eval(&block)
|
52
|
+
end
|
53
|
+
|
54
|
+
# and now we make sure we change it
|
55
|
+
execute unless @rolledback
|
56
|
+
@txn = nil
|
57
|
+
end
|
58
|
+
rescue => error
|
59
|
+
raise error
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
public
|
64
|
+
|
65
|
+
def initialize repository,
|
66
|
+
graph_name: nil, mutable: false, **options, &block
|
67
|
+
@repository = repository
|
68
|
+
@snapshot =
|
69
|
+
repository.supports?(:snapshots) ? repository.snapshot : repository
|
70
|
+
@options = options.dup
|
71
|
+
@mutable = mutable
|
72
|
+
@graph_name = graph_name
|
73
|
+
|
74
|
+
raise TransactionError,
|
75
|
+
'Tried to open a mutable transaction on an immutable repository' if
|
76
|
+
@mutable && !@repository.mutable?
|
77
|
+
|
78
|
+
@changes = RDF::Changeset.new
|
79
|
+
|
80
|
+
#warn caller[0]
|
81
|
+
|
82
|
+
wrap_txn(&block) if block_given?
|
83
|
+
end
|
84
|
+
|
85
|
+
def execute
|
86
|
+
raise TransactionError,
|
87
|
+
'Cannot execute a rolled back transaction. Open a new one instead.' if
|
88
|
+
@rolledback
|
89
|
+
|
90
|
+
ret = if @txn
|
91
|
+
@changes.apply(@repository)
|
92
|
+
else
|
93
|
+
wrap_txn { @changes.apply(@repository) }
|
94
|
+
end
|
95
|
+
|
96
|
+
@changes = RDF::Changeset.new
|
97
|
+
|
98
|
+
ret
|
99
|
+
end
|
100
|
+
|
101
|
+
def rollback
|
102
|
+
if @txn
|
103
|
+
@txn.abort
|
104
|
+
@txn = nil
|
105
|
+
end
|
106
|
+
|
107
|
+
super
|
108
|
+
end
|
109
|
+
end
|
110
|
+
|
111
|
+
#
|
112
|
+
# RDF::LMDB::Repository implements a lightweight, transactional,
|
113
|
+
# locally-attached data store using Symax LMDB.
|
114
|
+
#
|
115
|
+
class Repository < ::RDF::Repository
|
116
|
+
private
|
117
|
+
|
118
|
+
DEFAULT_TX_CLASS = RDF::LMDB::Transaction
|
119
|
+
|
120
|
+
SUPPORTS = %i[
|
121
|
+
graph_name literal_equality atomic_writes
|
122
|
+
].map {|s| [s, s] }.to_h.freeze
|
123
|
+
|
124
|
+
# give us the binary hash of the initial sha256 state
|
125
|
+
NULL_SHA256 = [
|
126
|
+
'e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855'
|
127
|
+
].pack('H*').freeze
|
128
|
+
|
129
|
+
def init_lmdb dir, **options
|
130
|
+
dir = Pathname(dir).expand_path
|
131
|
+
dir.mkdir unless dir.exist?
|
132
|
+
|
133
|
+
# fire up the environment
|
134
|
+
@lmdb = ::LMDB.new dir, **options
|
135
|
+
|
136
|
+
# XXX trip over the old database layout for now
|
137
|
+
dbs = @lmdb.database.keys.map(&:to_sym)
|
138
|
+
unless dbs.empty? or dbs.include? :int2term
|
139
|
+
err = <<-ERR.tr_s("\n ", ' ')
|
140
|
+
This version uses an updated (and incompatible) database layout.
|
141
|
+
Currently you have to dump from the old layout and reload the new one. Sorry!
|
142
|
+
ERR
|
143
|
+
raise ArgumentError, err
|
144
|
+
end
|
145
|
+
|
146
|
+
# databases are opened in a transaction, who knew
|
147
|
+
@lmdb.transaction do # |t|
|
148
|
+
@dbs = {
|
149
|
+
statement: [:integerkey], # key: int; val: ints
|
150
|
+
hash2term: [], # key: sha256, val: int
|
151
|
+
int2term: [:integerkey], # key: int, val: string
|
152
|
+
ints2stmt: [], # key: 3x ints, val: int
|
153
|
+
s2stmt: [:integerkey, :dupsort, :dupfixed],
|
154
|
+
p2stmt: [:integerkey, :dupsort, :dupfixed],
|
155
|
+
o2stmt: [:integerkey, :dupsort, :dupfixed],
|
156
|
+
g2stmt: [:integerkey, :dupsort, :dupfixed],
|
157
|
+
stmt2g: [:integerkey, :dupsort, :dupfixed],
|
158
|
+
sp2stmt: [:dupsort, :dupfixed],
|
159
|
+
so2stmt: [:dupsort, :dupfixed],
|
160
|
+
po2stmt: [:dupsort, :dupfixed],
|
161
|
+
# on the fence about whether or not to include graph
|
162
|
+
# indexes; my inclination is that they would be redundant
|
163
|
+
# gs2stmt: [:dupsort, :dupfixed],
|
164
|
+
# gp2stmt: [:dupsort, :dupfixed],
|
165
|
+
# go2stmt: [:dupsort, :dupfixed],
|
166
|
+
}.map do |name, flags|
|
167
|
+
[name, @lmdb.database(name.to_s,
|
168
|
+
**(flags + [:create]).map { |f| [f, true] }.to_h)]
|
169
|
+
end.to_h
|
170
|
+
|
171
|
+
# t.commit
|
172
|
+
end
|
173
|
+
@lmdb.sync
|
174
|
+
end
|
175
|
+
|
176
|
+
SPO = %i[subject predicate object].freeze
|
177
|
+
SPO_MAP = {
|
178
|
+
subject: :s2stmt,
|
179
|
+
predicate: :p2stmt,
|
180
|
+
object: :o2stmt,
|
181
|
+
}.freeze
|
182
|
+
SPOG_MAP = SPO_MAP.merge({ graph_name: :g2stmt }).freeze
|
183
|
+
PAIR_MAP = {
|
184
|
+
[:subject, :predicate] => :sp2stmt,
|
185
|
+
[:predicate, :object] => :po2stmt,
|
186
|
+
[:subject, :object] => :so2stmt,
|
187
|
+
# [:graph_name, :subject] => :gs2stmt,
|
188
|
+
# [:graph_name, :predicate] => :gp2stmt,
|
189
|
+
# [:graph_name, :object] => :go2stmt,
|
190
|
+
}.freeze
|
191
|
+
|
192
|
+
def last_key db
|
193
|
+
db = @dbs[db] if db.is_a? Symbol
|
194
|
+
return nil if db.size == 0
|
195
|
+
# the last entry in the database should be the highest number
|
196
|
+
db.cursor { |c| c.last }.first.unpack1 ?J
|
197
|
+
end
|
198
|
+
|
199
|
+
def int_for term
|
200
|
+
case term
|
201
|
+
when nil then 0
|
202
|
+
when RDF::Statement
|
203
|
+
terms = term.to_a.map { |t| int_for t }
|
204
|
+
return if terms.include? nil # the statement implicitly not here
|
205
|
+
|
206
|
+
if raw = @dbs[:ints2stmt].get(terms.pack 'J3')
|
207
|
+
raw.unpack1 ?J
|
208
|
+
end
|
209
|
+
when Hash # of integers
|
210
|
+
if raw = @dbs[:ints2stmt].get(term.values_at(*SPO).pack 'J3')
|
211
|
+
raw.unpack1 ?J
|
212
|
+
end
|
213
|
+
when RDF::Term
|
214
|
+
thash = hash_term term
|
215
|
+
if raw = @dbs[:hash2term].get(thash)
|
216
|
+
raw.unpack1 ?J
|
217
|
+
end
|
218
|
+
when String
|
219
|
+
# assume this is the hash string
|
220
|
+
if raw = @dbs[:hash2term].get(term)
|
221
|
+
raw.unpack1 ?J
|
222
|
+
end
|
223
|
+
end
|
224
|
+
end
|
225
|
+
|
226
|
+
def store_term term
|
227
|
+
return 0 if term.nil?
|
228
|
+
raise ArgumentError, 'must be a term' unless term.is_a? RDF::Term
|
229
|
+
# get the hash first
|
230
|
+
thash = hash_term term
|
231
|
+
if ix = int_for(thash)
|
232
|
+
return ix
|
233
|
+
end
|
234
|
+
|
235
|
+
# this should start with 1, not zero
|
236
|
+
ix = (last_key(@dbs[:int2term]) || 0) + 1
|
237
|
+
ib = [ix].pack ?J
|
238
|
+
@dbs[:int2term].put ib, term.to_ntriples.to_nfc
|
239
|
+
|
240
|
+
# we need the hash too to resolve the term the other way
|
241
|
+
@dbs[:hash2term].put thash, ib
|
242
|
+
|
243
|
+
ix # return the current index
|
244
|
+
end
|
245
|
+
|
246
|
+
def store_stmt statement, ints = nil
|
247
|
+
ints ||= statement.to_h.transform_values { |v| store_term v }
|
248
|
+
ik = ints.values_at(*SPO).pack 'J3'
|
249
|
+
if ib = @dbs[:ints2stmt].get(ik)
|
250
|
+
return ib.unpack1 ?J
|
251
|
+
end
|
252
|
+
|
253
|
+
# this should start with 1, not zero
|
254
|
+
ix = (last_key(:statement) || 0) + 1
|
255
|
+
ib = [ix].pack ?J
|
256
|
+
|
257
|
+
@dbs[:statement].put ib, ik # number to triple-number
|
258
|
+
@dbs[:ints2stmt].put ik, ib # triple-number to number
|
259
|
+
|
260
|
+
ix # the index integer
|
261
|
+
end
|
262
|
+
|
263
|
+
# everything gets normalized to NFC on the way in (i
|
264
|
+
# consternated for a very long time about NFC vs NFKC)
|
265
|
+
def hash_term term
|
266
|
+
Digest::SHA256.digest term.to_ntriples.to_nfc
|
267
|
+
end
|
268
|
+
|
269
|
+
# note we leave the period but we nuke the newline
|
270
|
+
def hash_statement stmt
|
271
|
+
Digest::SHA256.digest stmt.to_ntriples.to_nfc.chomp
|
272
|
+
end
|
273
|
+
|
274
|
+
def add_one statement
|
275
|
+
# get the integer keys for the terms and statement
|
276
|
+
terms = statement.to_h
|
277
|
+
ints = terms.transform_values { |v| store_term v }
|
278
|
+
ipack = ints.transform_values { |v| [v].pack ?J }
|
279
|
+
sint = store_stmt statement, ints
|
280
|
+
spack = [sint].pack ?J
|
281
|
+
|
282
|
+
# now we map the SPO indices
|
283
|
+
SPO_MAP.each do |k, d|
|
284
|
+
db = @dbs[d]
|
285
|
+
ik = ipack[k]
|
286
|
+
# note we test before inserting or lmdb will dutifully
|
287
|
+
# create unlimited duplicate values and results will be wrong
|
288
|
+
db.put ik, spack unless db.has? ik, spack
|
289
|
+
end
|
290
|
+
|
291
|
+
# now we do the pair indices
|
292
|
+
PAIR_MAP.each do |pair, d|
|
293
|
+
db = @dbs[d]
|
294
|
+
ik = ipack.values_at(*pair).join
|
295
|
+
db.put ik, spack unless db.has? ik, spack
|
296
|
+
end
|
297
|
+
|
298
|
+
# associate the statement with its graph; note zero is the null graph
|
299
|
+
gint = ints[:graph_name] || 0
|
300
|
+
gpack = [gint].pack ?J
|
301
|
+
@dbs[:g2stmt].put gpack, spack unless @dbs[:g2stmt].has? gpack, spack
|
302
|
+
@dbs[:stmt2g].put spack, gpack unless @dbs[:stmt2g].has? spack, gpack
|
303
|
+
end
|
304
|
+
|
305
|
+
def rm_one statement, scan: true
|
306
|
+
terms = statement.to_h
|
307
|
+
ints = terms.transform_values { |v| int_for v }
|
308
|
+
# if none of the terms resolve, we don't have it
|
309
|
+
return [] if ints.values_at(*SPO).include? nil
|
310
|
+
# same goes for the statement
|
311
|
+
sint = int_for(ints) or return []
|
312
|
+
spack = [sint].pack ?J
|
313
|
+
|
314
|
+
|
315
|
+
gint = ints[:graph_name] or return []
|
316
|
+
gpack = [gint].pack ?J
|
317
|
+
graphs = @dbs[:stmt2g].each_value(spack).to_a.uniq
|
318
|
+
|
319
|
+
out = []
|
320
|
+
unless graphs.empty?
|
321
|
+
# this will dissociate the statement from the graph
|
322
|
+
@dbs[:g2stmt].delete? gpack, spack
|
323
|
+
@dbs[:stmt2g].delete? spack, gpack
|
324
|
+
|
325
|
+
if graphs.size == 1 and graphs.first == gpack
|
326
|
+
# nuke the statement if this is the only instance of it
|
327
|
+
@dbs[:statement].delete? spack
|
328
|
+
@dbs[:ints2stmt].delete? ints.values_at(*SPO).pack('J3')
|
329
|
+
|
330
|
+
# now we nuke the indexes
|
331
|
+
|
332
|
+
# first the original spo
|
333
|
+
SPO_MAP.map do |k, d|
|
334
|
+
ib = [ints[k]].pack ?J
|
335
|
+
@dbs[d].delete? ib, spack
|
336
|
+
out << ints[k]
|
337
|
+
end
|
338
|
+
|
339
|
+
# add the graph if it is not null
|
340
|
+
out << terms[:graph_name] if terms[:graph_name] and gint != 0
|
341
|
+
|
342
|
+
# and now the pair map
|
343
|
+
ipack = ints.slice(*SPO).transform_values { |v| [v].pack ?J }
|
344
|
+
PAIR_MAP.map do |pair, d|
|
345
|
+
ib = ipack.values_at(*pair).join
|
346
|
+
@dbs[d].delete? ib, spack
|
347
|
+
end
|
348
|
+
end
|
349
|
+
end
|
350
|
+
|
351
|
+
# nuke any unused terms
|
352
|
+
clean_terms out if scan
|
353
|
+
|
354
|
+
out
|
355
|
+
end
|
356
|
+
|
357
|
+
def clean_terms terms
|
358
|
+
terms.map! { |t| t.is_a?(RDF::Term) ? hash_term(t) : t.to_s }.uniq
|
359
|
+
@lmdb.transaction do
|
360
|
+
terms.each do |hash|
|
361
|
+
next if hash == NULL_SHA256
|
362
|
+
next unless ib = @dbs[:hash2term].get(hash)
|
363
|
+
unless SPOG_MAP.values.any? {|d| @dbs[d].get ib }
|
364
|
+
@dbs[:int2term].delete? ib
|
365
|
+
@dbs[:hash2term].delete? hash
|
366
|
+
end
|
367
|
+
end
|
368
|
+
end
|
369
|
+
end
|
370
|
+
|
371
|
+
def complete! statement
|
372
|
+
raise ArgumentError, "Statement #{statement.inspect} is incomplete" if
|
373
|
+
statement.incomplete?
|
374
|
+
end
|
375
|
+
|
376
|
+
def resolve_term candidate, cache: {}, write: false
|
377
|
+
int = nil
|
378
|
+
term = case candidate
|
379
|
+
when nil then return
|
380
|
+
when Integer
|
381
|
+
int = candidate
|
382
|
+
return if int == 0
|
383
|
+
return cache[int] if cache[int]
|
384
|
+
str = [int].pack ?J
|
385
|
+
@dbs[:int2term][str] or return
|
386
|
+
when String
|
387
|
+
int = candidate.unpack1 ?J
|
388
|
+
str = [int].pack ?J
|
389
|
+
if candidate == str
|
390
|
+
return if int == 0
|
391
|
+
return cache[int] if cache[int]
|
392
|
+
@dbs[:int2term][str] or return
|
393
|
+
else
|
394
|
+
return if candidate == NULL_SHA256
|
395
|
+
str = @dbs[:hash2term][candidate] or return
|
396
|
+
@dbs[:int2term][str] or return
|
397
|
+
int = str.unpack1 ?J
|
398
|
+
end
|
399
|
+
else
|
400
|
+
raise ArgumentError, 'not an integer or a string'
|
401
|
+
end
|
402
|
+
|
403
|
+
term.force_encoding 'utf-8'
|
404
|
+
|
405
|
+
term = RDF::NTriples::Reader.parse_object term, intern: true
|
406
|
+
cache[int] = term if write
|
407
|
+
term
|
408
|
+
end
|
409
|
+
|
410
|
+
def split_fixed string, length
|
411
|
+
string = string.dup
|
412
|
+
seq = []
|
413
|
+
until string.empty?
|
414
|
+
seq << string.slice!(0, length)
|
415
|
+
end
|
416
|
+
seq
|
417
|
+
end
|
418
|
+
|
419
|
+
def resolve_terms string, cache: {}, write: false, hash: false
|
420
|
+
seq = []
|
421
|
+
out = string.unpack('J*').map do |i|
|
422
|
+
seq << i
|
423
|
+
j = resolve_term(i, cache: cache, write: write)
|
424
|
+
[i, j]
|
425
|
+
end.to_h
|
426
|
+
|
427
|
+
# if we aren't returning a hash, make sure the result is
|
428
|
+
# returned in order
|
429
|
+
hash ? out : out.values_at(*seq)
|
430
|
+
end
|
431
|
+
|
432
|
+
def each_maybe_with_graph has_graph = false, &block
|
433
|
+
body = -> do
|
434
|
+
cache = {}
|
435
|
+
@dbs[:statement].each do |spack, spo|
|
436
|
+
spo = resolve_terms spo, cache: cache, write: true
|
437
|
+
|
438
|
+
@dbs[:stmt2g].each_value spack do |gpack|
|
439
|
+
gint = gpack.unpack1 ?J
|
440
|
+
next if has_graph and gint == 0
|
441
|
+
graph = resolve_term gpack, cache: cache, write: true
|
442
|
+
block.call RDF::Statement(*spo, graph_name: graph)
|
443
|
+
end
|
444
|
+
end
|
445
|
+
end
|
446
|
+
|
447
|
+
@lmdb.transaction do
|
448
|
+
body.call
|
449
|
+
end
|
450
|
+
|
451
|
+
#@lmdb.active_txn ? body.call : @lmdb.transaction(true, &body)
|
452
|
+
end
|
453
|
+
|
454
|
+
def check_triple_quad arg, name: :triple, quad: false
|
455
|
+
raise ArgumentError, "#{name} must be Array-able" unless
|
456
|
+
arg.respond_to? :to_a
|
457
|
+
arg = arg.to_a
|
458
|
+
spo = arg.take 3
|
459
|
+
raise ArgumentError,
|
460
|
+
'#{name} must be at least 3 RDF::Term elements' unless
|
461
|
+
spo.length == 3 and spo.all? { |x| x.is_a? RDF::Term }
|
462
|
+
graph = nil
|
463
|
+
if quad
|
464
|
+
graph = arg[3]
|
465
|
+
raise ArgumentError, 'quad must be nil or an RDF::Term' unless
|
466
|
+
graph.nil? or graph.is_a? RDF::Term
|
467
|
+
end
|
468
|
+
|
469
|
+
RDF::Statement(*spo, graph_name: graph)
|
470
|
+
end
|
471
|
+
|
472
|
+
protected
|
473
|
+
|
474
|
+
def begin_transaction mutable: false, graph_name: nil, &block
|
475
|
+
@tx_class.new self, mutable: mutable, graph_name: graph_name, &block
|
476
|
+
end
|
477
|
+
|
478
|
+
def commit_transaction txn = nil
|
479
|
+
nil # nothing lol
|
480
|
+
end
|
481
|
+
|
482
|
+
def rollback_transaction txn = nil
|
483
|
+
nil # nothing lol
|
484
|
+
end
|
485
|
+
|
486
|
+
def query_pattern pattern, options = {}, &block
|
487
|
+
return enum_for :query_pattern, pattern, options unless block_given?
|
488
|
+
|
489
|
+
# coerce to hash
|
490
|
+
pattern = pattern.to_h
|
491
|
+
|
492
|
+
# flag if the graph is a variable
|
493
|
+
gv = pattern[:graph_name] && pattern[:graph_name].variable?
|
494
|
+
|
495
|
+
# hash of terms we get from the pattern
|
496
|
+
thash = pattern.reject { |_, v| !v or v.variable? }
|
497
|
+
|
498
|
+
# if nothing in the pattern is present then this is the same
|
499
|
+
# as #each/#each_statement
|
500
|
+
return each_maybe_with_graph(gv, &block) if thash.empty?
|
501
|
+
|
502
|
+
# hash of integer keys we retrieve for the terms
|
503
|
+
ihash = thash.transform_values { |v| int_for v }
|
504
|
+
cache = thash.keys.map { |k| [ihash[k], thash[k]] }.to_h
|
505
|
+
|
506
|
+
body = -> do
|
507
|
+
# if the graph is nonexistent there is nothing to show
|
508
|
+
return if thash[:graph_name] and !ihash[:graph_name]
|
509
|
+
|
510
|
+
if (SPO - thash.keys).empty?
|
511
|
+
# if all of SPO are defined then we can just construct a
|
512
|
+
# statement and hash it; then if G is defined on top of that
|
513
|
+
# we can just check :stmt2g
|
514
|
+
stmt = RDF::Statement.new(**thash)
|
515
|
+
sint = int_for(stmt) or return
|
516
|
+
spack = [sint].pack ?J
|
517
|
+
first = @dbs[:statement].get(spack) or return
|
518
|
+
|
519
|
+
# warn thash.inspect, ihash.inspect
|
520
|
+
|
521
|
+
# note
|
522
|
+
if gint = ihash[:graph_name]
|
523
|
+
gpack = [gint].pack ?J
|
524
|
+
return unless @dbs[:stmt2g].has? spack, gpack
|
525
|
+
yield stmt
|
526
|
+
else
|
527
|
+
@dbs[:stmt2g].each_value spack do |gpack|
|
528
|
+
# return if gpack.unpack1(?J) == 0
|
529
|
+
graph = resolve_term gpack, cache: cache, write: true
|
530
|
+
yield RDF::Statement.from(stmt, graph_name: graph)
|
531
|
+
end
|
532
|
+
end
|
533
|
+
elsif thash.keys.count == 1
|
534
|
+
# if only a single component (e.g. :subject) is present then
|
535
|
+
# we only need to check (e.g.) :s2stmt.
|
536
|
+
pos = thash.keys.first
|
537
|
+
db = @dbs[SPOG_MAP[pos]]
|
538
|
+
ix = ihash[pos] or return # note ihash[pos] may be nil
|
539
|
+
anchor = [ix].pack ?J
|
540
|
+
return unless db.has? anchor
|
541
|
+
|
542
|
+
db.each_value anchor do |spack|
|
543
|
+
spo = resolve_terms @dbs[:statement][spack],
|
544
|
+
cache: cache, write: true
|
545
|
+
if pos == :graph_name
|
546
|
+
yield RDF::Statement(*spo, graph_name: thash[:graph_name])
|
547
|
+
else
|
548
|
+
@dbs[:stmt2g].each_value spack do |gpack|
|
549
|
+
gint = gpack.unpack1 ?J
|
550
|
+
graph = resolve_term gint, cache: cache, write: true
|
551
|
+
yield RDF::Statement(*spo, graph_name: graph)
|
552
|
+
end
|
553
|
+
end
|
554
|
+
end
|
555
|
+
elsif thash.keys.count == 2 and thash[:graph_name]
|
556
|
+
pos = (thash.keys - [:graph_name]).first
|
557
|
+
db = @dbs[SPO_MAP[pos]]
|
558
|
+
ix = ihash[pos] or return
|
559
|
+
anchor = [ix].pack ?J
|
560
|
+
return unless db.has? anchor
|
561
|
+
|
562
|
+
db.each_value anchor do |spack|
|
563
|
+
spo = @dbs[:statement][spack]
|
564
|
+
return unless @dbs[:stmt2g].has? spack, ihash[:graph_name]
|
565
|
+
spo = resolve_terms spo
|
566
|
+
yield RDF::Statement(*spo, graph_name: thash[:graph_name])
|
567
|
+
end
|
568
|
+
else
|
569
|
+
# okay we will have either two or three terms
|
570
|
+
|
571
|
+
# select the pair of term keys with the lowest non-zero
|
572
|
+
# cardinality
|
573
|
+
pair = PAIR_MAP.select do |pr, _|
|
574
|
+
# we check for keys present as well as values (eg nil graph)
|
575
|
+
(pr - thash.keys).empty? and ihash.values_at(*pr).none?(&:nil?)
|
576
|
+
end.map do |pr, _|
|
577
|
+
v = ihash.values_at(*pr).pack 'J2'
|
578
|
+
c = @dbs[PAIR_MAP[pr]].cardinality(v)
|
579
|
+
[c, pr]
|
580
|
+
end.sort do |a, b|
|
581
|
+
a.first <=> b.first
|
582
|
+
end.reject { |x| x.first == 0 }.map(&:last).first or return
|
583
|
+
|
584
|
+
# grab the graph if we have it
|
585
|
+
g = resolve_term(ihash[:graph_name],
|
586
|
+
cache: cache, write: true) if ihash[:graph_name]
|
587
|
+
|
588
|
+
ib = ihash.values_at(*pair).pack 'J2'
|
589
|
+
@dbs[PAIR_MAP[pair]].each_value ib do |spack|
|
590
|
+
spo = resolve_terms @dbs[:statement][spack],
|
591
|
+
cache: cache, write: true
|
592
|
+
|
593
|
+
if ihash[:graph_name]
|
594
|
+
# warn g, ihash.inspect
|
595
|
+
gpack = [ihash[:graph_name]].pack ?J
|
596
|
+
next unless @dbs[:stmt2g].has? spack, gpack
|
597
|
+
yield RDF::Statement(*spo, graph_name: g)
|
598
|
+
else
|
599
|
+
@dbs[:stmt2g].each_value spack do |gpack|
|
600
|
+
gint = gpack.unpack1 ?J
|
601
|
+
g = resolve_term gint, cache: cache, write: true
|
602
|
+
yield RDF::Statement(*spo, graph_name: g)
|
603
|
+
end
|
604
|
+
end
|
605
|
+
end
|
606
|
+
end
|
607
|
+
end
|
608
|
+
|
609
|
+
#@lmdb.active_txn ? body.call : @lmdb.transaction(true, &body)
|
610
|
+
|
611
|
+
ret = nil
|
612
|
+
@lmdb.transaction do
|
613
|
+
ret = body.call
|
614
|
+
end
|
615
|
+
|
616
|
+
ret
|
617
|
+
end
|
618
|
+
|
619
|
+
public
|
620
|
+
|
621
|
+
def initialize dir = nil, uri: nil, title: nil, **options, &block
|
622
|
+
dir ||= options.delete(:dir) if options[:dir]
|
623
|
+
|
624
|
+
# wtf no idea why this won't inherit
|
625
|
+
@tx_class ||= options.delete(:transaction_class) { DEFAULT_TX_CLASS }
|
626
|
+
raise ArgumentError, "Invalid transaction class #{@tx_class}" unless
|
627
|
+
@tx_class.is_a? Class and @tx_class <= DEFAULT_TX_CLASS
|
628
|
+
|
629
|
+
init_lmdb dir, **options
|
630
|
+
super uri: uri, title: title, **options, &block
|
631
|
+
end
|
632
|
+
|
633
|
+
# housekeeping
|
634
|
+
|
635
|
+
def supports? feature
|
636
|
+
!!SUPPORTS[feature.to_s.to_sym]
|
637
|
+
end
|
638
|
+
|
639
|
+
def isolation_level
|
640
|
+
:serializable
|
641
|
+
end
|
642
|
+
|
643
|
+
def path
|
644
|
+
Pathname(@lmdb.path)
|
645
|
+
end
|
646
|
+
|
647
|
+
def clear
|
648
|
+
@lmdb.transaction do
|
649
|
+
@dbs.each_value { |db| db.clear }
|
650
|
+
end
|
651
|
+
# we do not clear the main database; that nukes the sub-databases
|
652
|
+
# @lmdb.database.clear
|
653
|
+
end
|
654
|
+
|
655
|
+
def open dir, **options
|
656
|
+
init_lmdb dir, **options
|
657
|
+
end
|
658
|
+
|
659
|
+
def close
|
660
|
+
@lmdb.close
|
661
|
+
end
|
662
|
+
|
663
|
+
# data manipulation
|
664
|
+
|
665
|
+
def insert_statement statement
|
666
|
+
complete! statement
|
667
|
+
@lmdb.transaction { |t| add_one statement; t.commit }
|
668
|
+
nil
|
669
|
+
end
|
670
|
+
|
671
|
+
def delete_statement statement
|
672
|
+
complete! statement
|
673
|
+
@lmdb.transaction { |t| rm_one statement; t.commit }
|
674
|
+
nil
|
675
|
+
end
|
676
|
+
|
677
|
+
def insert_statements statements
|
678
|
+
@lmdb.transaction do
|
679
|
+
statements.each do |statement|
|
680
|
+
complete! statement
|
681
|
+
add_one statement
|
682
|
+
end
|
683
|
+
end
|
684
|
+
|
685
|
+
nil
|
686
|
+
end
|
687
|
+
|
688
|
+
def delete_statements statements
|
689
|
+
@lmdb.transaction do |t|
|
690
|
+
hashes = []
|
691
|
+
statements.each do |statement|
|
692
|
+
complete! statement
|
693
|
+
hashes += rm_one statement, scan: false
|
694
|
+
end
|
695
|
+
|
696
|
+
clean_terms hashes
|
697
|
+
t.commit
|
698
|
+
end
|
699
|
+
|
700
|
+
nil
|
701
|
+
end
|
702
|
+
|
703
|
+
# data retrieval
|
704
|
+
|
705
|
+
def each &block
|
706
|
+
return enum_for :each unless block_given?
|
707
|
+
|
708
|
+
each_maybe_with_graph(&block)
|
709
|
+
end
|
710
|
+
|
711
|
+
def each_subject &block
|
712
|
+
return enum_for :each_subject unless block_given?
|
713
|
+
@dbs[:s2stmt].cursor do |c|
|
714
|
+
while (k, _ = c.next true)
|
715
|
+
yield resolve_term k
|
716
|
+
end
|
717
|
+
end
|
718
|
+
end
|
719
|
+
|
720
|
+
def each_predicate &block
|
721
|
+
return enum_for :each_predicate unless block_given?
|
722
|
+
@dbs[:p2stmt].cursor do |c|
|
723
|
+
while (k, _ = c.next true)
|
724
|
+
yield resolve_term k
|
725
|
+
end
|
726
|
+
end
|
727
|
+
end
|
728
|
+
|
729
|
+
def each_object &block
|
730
|
+
return enum_for :each_object unless block_given?
|
731
|
+
@dbs[:o2stmt].cursor do |c|
|
732
|
+
while (k, _ = c.next true)
|
733
|
+
yield resolve_term k
|
734
|
+
end
|
735
|
+
end
|
736
|
+
end
|
737
|
+
|
738
|
+
def each_graph &block
|
739
|
+
return enum_for :each_graph unless block_given?
|
740
|
+
@dbs[:g2stmt].cursor do |c|
|
741
|
+
while (k, _ = c.next true)
|
742
|
+
yield RDF::Graph.new(graph_name: resolve_term(k), data: self)
|
743
|
+
end
|
744
|
+
end
|
745
|
+
end
|
746
|
+
|
747
|
+
def each_term &block
|
748
|
+
return enum_for :each_term unless block_given?
|
749
|
+
@dbs[:int2term].cursor do |c|
|
750
|
+
while (_, v = c.next)
|
751
|
+
# yield RDF::NTriples::Reader.unserialize v
|
752
|
+
v.force_encoding 'utf-8'
|
753
|
+
yield RDF::NTriples::Reader.parse_object(v, intern: true)
|
754
|
+
end
|
755
|
+
end
|
756
|
+
end
|
757
|
+
|
758
|
+
def project_graph graph_name, &block
|
759
|
+
return enum_for :project_graph, graph_name unless block_given?
|
760
|
+
body = -> do
|
761
|
+
gint = graph_name ? int_for(graph_name) : 0
|
762
|
+
return unless gint
|
763
|
+
gpack = [gint].pack ?J
|
764
|
+
cache = {}
|
765
|
+
@dbs[:statement].each do |spack, spo|
|
766
|
+
next unless @dbs[:stmt2g].has? spack, gpack
|
767
|
+
spo = resolve_terms spo, cache: cache, write: true
|
768
|
+
|
769
|
+
block.call RDF::Statement(*spo, graph_name: graph_name)
|
770
|
+
end
|
771
|
+
end
|
772
|
+
|
773
|
+
@lmdb.transaction do
|
774
|
+
body.call
|
775
|
+
end
|
776
|
+
|
777
|
+
#@lmdb.active_txn ? body.call : @lmdb.transaction(true, &body)
|
778
|
+
end
|
779
|
+
|
780
|
+
def count
|
781
|
+
@dbs[:stmt2g].size
|
782
|
+
end
|
783
|
+
|
784
|
+
def empty?
|
785
|
+
count == 0
|
786
|
+
end
|
787
|
+
|
788
|
+
# def apply_changeset changeset
|
789
|
+
# @lmdb.transaction do |t|
|
790
|
+
# delete_insert(changeset.deletes, changeset.inserts)
|
791
|
+
# end
|
792
|
+
# end
|
793
|
+
|
794
|
+
def delete_insert deletes, inserts
|
795
|
+
ret = super(deletes, inserts)
|
796
|
+
commit_transaction # this is to satiate the test suite
|
797
|
+
ret
|
798
|
+
end
|
799
|
+
|
800
|
+
def env
|
801
|
+
@lmdb
|
802
|
+
end
|
803
|
+
|
804
|
+
def transaction mutable: false, &block
|
805
|
+
return begin_transaction mutable: mutable unless block_given?
|
806
|
+
|
807
|
+
begin
|
808
|
+
begin_transaction mutable: mutable, &block
|
809
|
+
rescue => error
|
810
|
+
rollback_transaction # to sate the test suite
|
811
|
+
raise error
|
812
|
+
end
|
813
|
+
#commit_transaction # to sate the test suite
|
814
|
+
self
|
815
|
+
end
|
816
|
+
|
817
|
+
def has_statement? statement
|
818
|
+
raise ArgumentError, 'Argument must be an RDF::Statement' unless
|
819
|
+
statement.is_a? RDF::Statement
|
820
|
+
!query_pattern(statement.to_h).to_a.empty?
|
821
|
+
end
|
822
|
+
|
823
|
+
def has_graph? graph_name
|
824
|
+
raise ArgumentError, 'graph_name must be an RDF::Term' unless
|
825
|
+
graph_name.is_a? RDF::Term
|
826
|
+
int = int_for(graph_name) or return
|
827
|
+
pack = [int].pack ?J
|
828
|
+
@dbs[:g2stmt].has? pack
|
829
|
+
end
|
830
|
+
|
831
|
+
def has_subject? subject
|
832
|
+
raise ArgumentError, 'subject must be an RDF::Term' unless
|
833
|
+
subject.is_a? RDF::Term
|
834
|
+
int = int_for(subject) or return
|
835
|
+
pack = [int].pack ?J
|
836
|
+
@dbs[:s2stmt].has? pack
|
837
|
+
end
|
838
|
+
|
839
|
+
def has_predicate? predicate
|
840
|
+
raise ArgumentError, 'predicate must be an RDF::Term' unless
|
841
|
+
predicate.is_a? RDF::Term
|
842
|
+
int = int_for(predicate) or return
|
843
|
+
pack = [int].pack ?J
|
844
|
+
@dbs[:p2stmt].has? pack
|
845
|
+
end
|
846
|
+
|
847
|
+
def has_object? object
|
848
|
+
raise ArgumentError, 'object must be an RDF::Term' unless
|
849
|
+
object.is_a? RDF::Term
|
850
|
+
int = int_for(object) or return
|
851
|
+
pack = [int].pack ?J
|
852
|
+
@dbs[:o2stmt].has? pack
|
853
|
+
end
|
854
|
+
|
855
|
+
def has_term? term
|
856
|
+
raise ArgumentError, 'term must be an RDF::Term' unless
|
857
|
+
term.is_a? RDF::Term
|
858
|
+
@dbs[:hash2term].has? hash_term(term)
|
859
|
+
end
|
860
|
+
|
861
|
+
def has_triple? triple
|
862
|
+
has_statement? check_triple_quad triple
|
863
|
+
end
|
864
|
+
|
865
|
+
def has_quad? quad
|
866
|
+
has_statement? check_triple_quad quad, quad: true
|
867
|
+
end
|
868
|
+
|
869
|
+
|
870
|
+
# lol, ruby
|
871
|
+
end
|
872
|
+
end
|
873
|
+
end
|