nomenklatura-mpt 4.1.9__py3-none-any.whl
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.
- nomenklatura/__init__.py +11 -0
- nomenklatura/cache.py +194 -0
- nomenklatura/cli.py +260 -0
- nomenklatura/conflicting_match.py +80 -0
- nomenklatura/data/er-unstable.pkl +0 -0
- nomenklatura/data/regression-v1.pkl +0 -0
- nomenklatura/db.py +139 -0
- nomenklatura/delta.py +4 -0
- nomenklatura/enrich/__init__.py +94 -0
- nomenklatura/enrich/aleph.py +141 -0
- nomenklatura/enrich/common.py +219 -0
- nomenklatura/enrich/nominatim.py +72 -0
- nomenklatura/enrich/opencorporates.py +233 -0
- nomenklatura/enrich/openfigi.py +124 -0
- nomenklatura/enrich/permid.py +201 -0
- nomenklatura/enrich/wikidata.py +268 -0
- nomenklatura/enrich/yente.py +116 -0
- nomenklatura/exceptions.py +9 -0
- nomenklatura/index/__init__.py +5 -0
- nomenklatura/index/common.py +24 -0
- nomenklatura/index/entry.py +89 -0
- nomenklatura/index/index.py +170 -0
- nomenklatura/index/tokenizer.py +92 -0
- nomenklatura/judgement.py +21 -0
- nomenklatura/kv.py +40 -0
- nomenklatura/matching/__init__.py +47 -0
- nomenklatura/matching/bench.py +32 -0
- nomenklatura/matching/compare/__init__.py +0 -0
- nomenklatura/matching/compare/addresses.py +71 -0
- nomenklatura/matching/compare/countries.py +15 -0
- nomenklatura/matching/compare/dates.py +83 -0
- nomenklatura/matching/compare/gender.py +15 -0
- nomenklatura/matching/compare/identifiers.py +30 -0
- nomenklatura/matching/compare/names.py +157 -0
- nomenklatura/matching/compare/util.py +51 -0
- nomenklatura/matching/compat.py +66 -0
- nomenklatura/matching/erun/__init__.py +0 -0
- nomenklatura/matching/erun/countries.py +42 -0
- nomenklatura/matching/erun/identifiers.py +64 -0
- nomenklatura/matching/erun/misc.py +71 -0
- nomenklatura/matching/erun/model.py +110 -0
- nomenklatura/matching/erun/names.py +126 -0
- nomenklatura/matching/erun/train.py +135 -0
- nomenklatura/matching/erun/util.py +28 -0
- nomenklatura/matching/logic_v1/__init__.py +0 -0
- nomenklatura/matching/logic_v1/identifiers.py +104 -0
- nomenklatura/matching/logic_v1/model.py +76 -0
- nomenklatura/matching/logic_v1/multi.py +21 -0
- nomenklatura/matching/logic_v1/phonetic.py +142 -0
- nomenklatura/matching/logic_v2/__init__.py +0 -0
- nomenklatura/matching/logic_v2/identifiers.py +124 -0
- nomenklatura/matching/logic_v2/model.py +98 -0
- nomenklatura/matching/logic_v2/names/__init__.py +3 -0
- nomenklatura/matching/logic_v2/names/analysis.py +51 -0
- nomenklatura/matching/logic_v2/names/distance.py +181 -0
- nomenklatura/matching/logic_v2/names/magic.py +60 -0
- nomenklatura/matching/logic_v2/names/match.py +195 -0
- nomenklatura/matching/logic_v2/names/pairing.py +81 -0
- nomenklatura/matching/logic_v2/names/util.py +89 -0
- nomenklatura/matching/name_based/__init__.py +4 -0
- nomenklatura/matching/name_based/misc.py +86 -0
- nomenklatura/matching/name_based/model.py +59 -0
- nomenklatura/matching/name_based/names.py +59 -0
- nomenklatura/matching/pairs.py +42 -0
- nomenklatura/matching/regression_v1/__init__.py +0 -0
- nomenklatura/matching/regression_v1/misc.py +75 -0
- nomenklatura/matching/regression_v1/model.py +110 -0
- nomenklatura/matching/regression_v1/names.py +63 -0
- nomenklatura/matching/regression_v1/train.py +87 -0
- nomenklatura/matching/regression_v1/util.py +31 -0
- nomenklatura/matching/svm_v1/__init__.py +5 -0
- nomenklatura/matching/svm_v1/misc.py +94 -0
- nomenklatura/matching/svm_v1/model.py +168 -0
- nomenklatura/matching/svm_v1/names.py +81 -0
- nomenklatura/matching/svm_v1/train.py +186 -0
- nomenklatura/matching/svm_v1/util.py +30 -0
- nomenklatura/matching/types.py +227 -0
- nomenklatura/matching/util.py +62 -0
- nomenklatura/publish/__init__.py +0 -0
- nomenklatura/publish/dates.py +49 -0
- nomenklatura/publish/edges.py +32 -0
- nomenklatura/py.typed +0 -0
- nomenklatura/resolver/__init__.py +6 -0
- nomenklatura/resolver/common.py +2 -0
- nomenklatura/resolver/edge.py +107 -0
- nomenklatura/resolver/identifier.py +60 -0
- nomenklatura/resolver/linker.py +101 -0
- nomenklatura/resolver/resolver.py +565 -0
- nomenklatura/settings.py +17 -0
- nomenklatura/store/__init__.py +41 -0
- nomenklatura/store/base.py +130 -0
- nomenklatura/store/level.py +272 -0
- nomenklatura/store/memory.py +102 -0
- nomenklatura/store/redis_.py +131 -0
- nomenklatura/store/sql.py +219 -0
- nomenklatura/store/util.py +48 -0
- nomenklatura/store/versioned.py +371 -0
- nomenklatura/tui/__init__.py +17 -0
- nomenklatura/tui/app.py +294 -0
- nomenklatura/tui/app.tcss +52 -0
- nomenklatura/tui/comparison.py +81 -0
- nomenklatura/tui/util.py +35 -0
- nomenklatura/util.py +26 -0
- nomenklatura/versions.py +119 -0
- nomenklatura/wikidata/__init__.py +14 -0
- nomenklatura/wikidata/client.py +122 -0
- nomenklatura/wikidata/lang.py +94 -0
- nomenklatura/wikidata/model.py +139 -0
- nomenklatura/wikidata/props.py +70 -0
- nomenklatura/wikidata/qualified.py +49 -0
- nomenklatura/wikidata/query.py +66 -0
- nomenklatura/wikidata/value.py +87 -0
- nomenklatura/xref.py +125 -0
- nomenklatura_mpt-4.1.9.dist-info/METADATA +159 -0
- nomenklatura_mpt-4.1.9.dist-info/RECORD +118 -0
- nomenklatura_mpt-4.1.9.dist-info/WHEEL +4 -0
- nomenklatura_mpt-4.1.9.dist-info/entry_points.txt +3 -0
- nomenklatura_mpt-4.1.9.dist-info/licenses/LICENSE +21 -0
nomenklatura/xref.py
ADDED
@@ -0,0 +1,125 @@
|
|
1
|
+
import logging
|
2
|
+
from typing import List, Optional, Type
|
3
|
+
from followthemoney import Schema, DS, SE
|
4
|
+
from pathlib import Path
|
5
|
+
|
6
|
+
from nomenklatura import Index
|
7
|
+
from nomenklatura.store import Store
|
8
|
+
from nomenklatura.judgement import Judgement
|
9
|
+
from nomenklatura.resolver import Resolver
|
10
|
+
from nomenklatura.index import BaseIndex
|
11
|
+
from nomenklatura.matching import DefaultAlgorithm, ScoringAlgorithm, ScoringConfig
|
12
|
+
from nomenklatura.conflicting_match import ConflictingMatchReporter
|
13
|
+
|
14
|
+
log = logging.getLogger(__name__)
|
15
|
+
|
16
|
+
|
17
|
+
def _print_stats(pairs: int, suggested: int, scores: List[float]) -> None:
|
18
|
+
matches = len(scores)
|
19
|
+
log.info(
|
20
|
+
"Xref: %d pairs, %d suggested, avg: %.2f, min: %.2f, max: %.2f",
|
21
|
+
pairs,
|
22
|
+
suggested,
|
23
|
+
sum(scores) / max(1, matches),
|
24
|
+
min(scores, default=0.0),
|
25
|
+
max(scores, default=0.0),
|
26
|
+
)
|
27
|
+
|
28
|
+
|
29
|
+
def xref(
|
30
|
+
resolver: Resolver[SE],
|
31
|
+
store: Store[DS, SE],
|
32
|
+
index_dir: Path,
|
33
|
+
index_type: Type[BaseIndex[DS, SE]] = Index,
|
34
|
+
limit: int = 5000,
|
35
|
+
limit_factor: int = 10,
|
36
|
+
scored: bool = True,
|
37
|
+
external: bool = True,
|
38
|
+
discount_internal: float = 0.7,
|
39
|
+
range: Optional[Schema] = None,
|
40
|
+
auto_threshold: Optional[float] = None,
|
41
|
+
conflicting_match_threshold: Optional[float] = None,
|
42
|
+
focus_dataset: Optional[str] = None,
|
43
|
+
algorithm: Type[ScoringAlgorithm] = DefaultAlgorithm,
|
44
|
+
config: Optional[ScoringConfig] = None,
|
45
|
+
user: Optional[str] = None,
|
46
|
+
) -> None:
|
47
|
+
log.info("Begin xref: %r, resolver: %s", store, resolver)
|
48
|
+
if config is None:
|
49
|
+
config = ScoringConfig.defaults()
|
50
|
+
view = store.default_view(external=external)
|
51
|
+
index = index_type(view, index_dir)
|
52
|
+
index.build()
|
53
|
+
conflict_reporter = None
|
54
|
+
if conflicting_match_threshold is not None:
|
55
|
+
conflict_reporter = ConflictingMatchReporter(
|
56
|
+
view, resolver, conflicting_match_threshold
|
57
|
+
)
|
58
|
+
|
59
|
+
try:
|
60
|
+
scores: List[float] = []
|
61
|
+
suggested = 0
|
62
|
+
idx = 0
|
63
|
+
resolver.begin()
|
64
|
+
pairs = index.pairs(max_pairs=limit * limit_factor)
|
65
|
+
for idx, ((left_id_, right_id_), score) in enumerate(pairs):
|
66
|
+
if idx % 1000 == 0 and idx > 0:
|
67
|
+
_print_stats(idx, suggested, scores)
|
68
|
+
|
69
|
+
if suggested % 10000 == 0 and suggested > 0:
|
70
|
+
resolver.commit()
|
71
|
+
resolver.begin()
|
72
|
+
|
73
|
+
left_id = resolver.get_canonical(left_id_)
|
74
|
+
right_id = resolver.get_canonical(right_id_)
|
75
|
+
if not resolver.check_candidate(left_id, right_id):
|
76
|
+
continue
|
77
|
+
|
78
|
+
left = view.get_entity(left_id)
|
79
|
+
right = view.get_entity(right_id)
|
80
|
+
if left is None or left.id is None or right is None or right.id is None:
|
81
|
+
continue
|
82
|
+
|
83
|
+
if not left.schema.can_match(right.schema):
|
84
|
+
continue
|
85
|
+
|
86
|
+
if range is not None:
|
87
|
+
if not left.schema.is_a(range) and not right.schema.is_a(range):
|
88
|
+
continue
|
89
|
+
|
90
|
+
if scored:
|
91
|
+
result = algorithm.compare(left, right, config)
|
92
|
+
score = result.score
|
93
|
+
if conflict_reporter is not None:
|
94
|
+
conflict_reporter.check_match(result.score, left_id, right_id)
|
95
|
+
|
96
|
+
scores.append(score)
|
97
|
+
|
98
|
+
if len(left.datasets.intersection(right.datasets)) > 0:
|
99
|
+
score = score * discount_internal
|
100
|
+
|
101
|
+
if auto_threshold is not None and score > auto_threshold:
|
102
|
+
log.info("Auto-merge [%.2f]: %s <> %s", score, left, right)
|
103
|
+
canonical_id = resolver.decide(
|
104
|
+
left_id, right_id, Judgement.POSITIVE, user=user
|
105
|
+
)
|
106
|
+
store.update(canonical_id)
|
107
|
+
continue
|
108
|
+
|
109
|
+
if focus_dataset in left.datasets and focus_dataset not in right.datasets:
|
110
|
+
score = (score + 1.0) / 2.0
|
111
|
+
if focus_dataset not in left.datasets and focus_dataset in right.datasets:
|
112
|
+
score = (score + 1.0) / 2.0
|
113
|
+
|
114
|
+
resolver.suggest(left.id, right.id, score, user=user)
|
115
|
+
|
116
|
+
if suggested >= limit:
|
117
|
+
break
|
118
|
+
suggested += 1
|
119
|
+
_print_stats(idx, suggested, scores)
|
120
|
+
resolver.commit()
|
121
|
+
|
122
|
+
if conflict_reporter is not None:
|
123
|
+
conflict_reporter.report()
|
124
|
+
except KeyboardInterrupt:
|
125
|
+
log.info("User cancelled, xref will end gracefully.")
|
@@ -0,0 +1,159 @@
|
|
1
|
+
Metadata-Version: 2.4
|
2
|
+
Name: nomenklatura_mpt
|
3
|
+
Version: 4.1.9
|
4
|
+
Summary: Make record linkages in followthemoney data.
|
5
|
+
Project-URL: Documentation, https://github.com/opensanctions/nomenklatura/
|
6
|
+
Project-URL: Repository, https://github.com/opensanctions/nomenklatura.git
|
7
|
+
Project-URL: Issues, https://github.com/opensanctions/nomenklatura/issues
|
8
|
+
Author-email: OpenSanctions <info@opensanctions.org>
|
9
|
+
License: Copyright (c) 2013-2022, Friedrich Lindenberg
|
10
|
+
Copyright (c) 2023-2025, OpenSanctions Datenbanken GmbH
|
11
|
+
|
12
|
+
Permission is hereby granted, free of charge, to any person obtaining a
|
13
|
+
copy of this software and associated documentation files (the
|
14
|
+
"Software"), to deal in the Software without restriction, including
|
15
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
16
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
17
|
+
permit persons to whom the Software is furnished to do so, subject to
|
18
|
+
the following conditions:
|
19
|
+
|
20
|
+
The above copyright notice and this permission notice shall be included
|
21
|
+
in all copies or substantial portions of the Software.
|
22
|
+
|
23
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
|
24
|
+
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
25
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
26
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
27
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
28
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
29
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
30
|
+
License-File: LICENSE
|
31
|
+
Classifier: Intended Audience :: Developers
|
32
|
+
Classifier: License :: OSI Approved :: MIT License
|
33
|
+
Classifier: Operating System :: OS Independent
|
34
|
+
Classifier: Programming Language :: Python :: 3.11
|
35
|
+
Classifier: Programming Language :: Python :: 3.12
|
36
|
+
Requires-Python: >=3.9
|
37
|
+
Requires-Dist: click
|
38
|
+
Requires-Dist: fingerprints
|
39
|
+
Requires-Dist: followthemoney
|
40
|
+
Requires-Dist: lxml
|
41
|
+
Requires-Dist: pydantic
|
42
|
+
Requires-Dist: rich
|
43
|
+
Requires-Dist: rigour
|
44
|
+
Requires-Dist: scikit-learn
|
45
|
+
Requires-Dist: shortuuid
|
46
|
+
Requires-Dist: sqlalchemy
|
47
|
+
Requires-Dist: textual
|
48
|
+
Provides-Extra: dev
|
49
|
+
Requires-Dist: build; extra == 'dev'
|
50
|
+
Requires-Dist: bump2version; extra == 'dev'
|
51
|
+
Requires-Dist: coverage>=4.1; extra == 'dev'
|
52
|
+
Requires-Dist: fakeredis; extra == 'dev'
|
53
|
+
Requires-Dist: flake8>=2.6.0; extra == 'dev'
|
54
|
+
Requires-Dist: lxml-stubs; extra == 'dev'
|
55
|
+
Requires-Dist: mypy; extra == 'dev'
|
56
|
+
Requires-Dist: plyvel<2.0.0; extra == 'dev'
|
57
|
+
Requires-Dist: psycopg2-binary; extra == 'dev'
|
58
|
+
Requires-Dist: pytest; extra == 'dev'
|
59
|
+
Requires-Dist: pytest-cov; extra == 'dev'
|
60
|
+
Requires-Dist: redis<7.0.0,>5.0.0; extra == 'dev'
|
61
|
+
Requires-Dist: requests-mock; extra == 'dev'
|
62
|
+
Requires-Dist: twine; extra == 'dev'
|
63
|
+
Requires-Dist: types-pyyaml; extra == 'dev'
|
64
|
+
Requires-Dist: types-redis; extra == 'dev'
|
65
|
+
Requires-Dist: types-requests; extra == 'dev'
|
66
|
+
Requires-Dist: types-setuptools; extra == 'dev'
|
67
|
+
Requires-Dist: wheel>=0.29.0; extra == 'dev'
|
68
|
+
Provides-Extra: leveldb
|
69
|
+
Requires-Dist: plyvel<2.0.0; extra == 'leveldb'
|
70
|
+
Provides-Extra: redis
|
71
|
+
Requires-Dist: redis<7.0.0,>5.0.0; extra == 'redis'
|
72
|
+
Description-Content-Type: text/markdown
|
73
|
+
|
74
|
+
# nomenklatura
|
75
|
+
|
76
|
+
Nomenklatura de-duplicates and integrates different [Follow the Money](https://followthemoney.tech/) entities. It serves to clean up messy data and to find links between different datasets.
|
77
|
+
|
78
|
+

|
79
|
+
|
80
|
+
## Usage
|
81
|
+
|
82
|
+
You can install `nomenklatura` via PyPI:
|
83
|
+
|
84
|
+
```bash
|
85
|
+
$ pip install nomenklatura
|
86
|
+
```
|
87
|
+
|
88
|
+
### Command-line usage
|
89
|
+
|
90
|
+
Much of the functionality of `nomenklatura` can be used as a command-line tool. In the following example, we'll assume that you have a file containing [Follow the Money](https://followthemoney.tech/) entities in your local directory, named `entities.ijson`. If you just want try it out, you can use the file `tests/fixtures/donations.ijson` in this repository for testing (it contains German campaign finance data).
|
91
|
+
|
92
|
+
With the file in place, you will cross-reference the entities to generate de-duplication candidates, then run the interactive de-duplication UI in your console, and eventually apply the judgements to generate a new file with merged entities:
|
93
|
+
|
94
|
+
```bash
|
95
|
+
# generate merge candidates using an in-memory index:
|
96
|
+
$ nomenklatura xref entities.ijson
|
97
|
+
# note there is now a sqlite database, `nomenklatura.db` that contains de-duplication info.
|
98
|
+
$ nomenklatura dedupe entities.ijson
|
99
|
+
# will pop up a user interface.
|
100
|
+
$ nomenklatura apply entities.ijson -o merged.ijson
|
101
|
+
# de-duplicated data goes into `merged.ijson`:
|
102
|
+
$ cat entities.ijson | wc -l
|
103
|
+
474
|
104
|
+
$ cat merged.ijson | wc -l
|
105
|
+
468
|
106
|
+
```
|
107
|
+
|
108
|
+
The resolver graph database location can be customised by setting the environment variable `NOMENKLATURA_DB_URL`
|
109
|
+
|
110
|
+
### Programmatic usage
|
111
|
+
|
112
|
+
The command-line use of `nomenklatura` is targeted at small datasets which need to be de-duplicated. For more involved scenarios, the package also offers a Python API which can be used to control the semantics of de-duplication.
|
113
|
+
|
114
|
+
* `nomenklatura.Dataset` - implements a basic dataset for describing a set of entities.
|
115
|
+
* `nomenklatura.Store` - a general purpose access mechanism for entities. By default, a store is used to access entity data stored in files as an in-memory cache, but the store can be subclassed to work with entities from a database system.
|
116
|
+
* `nomenklatura.Index` - a full-text in-memory search index for FtM entities. In the application, this is used to block de-duplication candidates, but the index can also be used to drive an API etc.
|
117
|
+
* `nomenklatura.index.TantivyIndex` - a wrapper around Tantivy for indexing and matching FtM entities.
|
118
|
+
* `nomenklatura.Resolver` - the core of the de-duplication process, the resolver is essentially a graph with edges made out of entity judgements. The resolver can be used to store judgements or get the canonical ID for a given entity.
|
119
|
+
|
120
|
+
All of the API classes have extensive type annotations, which should make their integration in any modern Python API simpler.
|
121
|
+
|
122
|
+
## Design
|
123
|
+
|
124
|
+
This package offers an implementation of an in-memory data deduplication framework centered around the FtM data model. The idea is the following workflow:
|
125
|
+
|
126
|
+
* Accept FtM-shaped entities from a given loader (e.g. a JSON file, or a database)
|
127
|
+
* Build an in-memory inverted index of the entities for dedupe blocking
|
128
|
+
* Generate merge candidates using the blocking index and FtM compare
|
129
|
+
* Provide a file-based storage format for merge challenges and decisions
|
130
|
+
* Provide a text-based user interface to let users make merge decisions
|
131
|
+
|
132
|
+
Later on, the following might be added:
|
133
|
+
|
134
|
+
* A web application to let users make merge decisions on the web
|
135
|
+
|
136
|
+
### Resolver graph
|
137
|
+
|
138
|
+
The key implementation detail of nomenklatura is the `Resolver`, a graph structure that
|
139
|
+
manages user decisions regarding entity identity. Edges are `Judgements` of whether
|
140
|
+
two entity IDs are the same, not the same, or undecided. The resolver implements an
|
141
|
+
algorithm for computing connected components, which can the be used to find the best
|
142
|
+
available ID for a cluster of entities. It can also be used to evaluate transitive
|
143
|
+
judgements, e.g. if A <> B, and B = C, then we don't need to ask if A = C.
|
144
|
+
|
145
|
+
## Reading
|
146
|
+
|
147
|
+
* https://dedupe.readthedocs.org/en/latest/
|
148
|
+
* https://github.com/OpenRefine/OpenRefine/wiki/Reconcilable-Data-Sources
|
149
|
+
* https://github.com/OpenRefine/OpenRefine/wiki/Clustering-In-Depth
|
150
|
+
* https://github.com/OpenRefine/OpenRefine/wiki/Reconciliation-Service-API
|
151
|
+
|
152
|
+
|
153
|
+
## Contact, contributions etc.
|
154
|
+
|
155
|
+
This codebase is licensed under the terms of an MIT license (see LICENSE).
|
156
|
+
|
157
|
+
We're keen for any contributions, bug fixes and feature suggestions, please use the GitHub issue tracker for this repository.
|
158
|
+
|
159
|
+
Nomenklatura is currently developed thanks to a Prototypefund grant for [OpenSanctions](https://opensanctions.org). Previous iterations of the package were developed with support from [Knight-Mozilla OpenNews](http://opennews.org) and the [Open Knowledge Foundation Labs](http://okfnlabs.org).
|
@@ -0,0 +1,118 @@
|
|
1
|
+
nomenklatura/__init__.py,sha256=x_RyOYXt3ua2EO33aK8-kjTXrJD1FmeX5Duhw7hPIj4,214
|
2
|
+
nomenklatura/cache.py,sha256=rpM1k3M1ExtvyasnA45_jRzBsNQfAg9B63LHL8n4cfY,6396
|
3
|
+
nomenklatura/cli.py,sha256=LXAL3WyHvu7n8nBPsHvCoc4EKlWqJo9NpxCAqG0VNNI,8677
|
4
|
+
nomenklatura/conflicting_match.py,sha256=-INZD5OIYTtPQqS1iB0Vcuy0jAS7kj08ghebQ04yUoA,3269
|
5
|
+
nomenklatura/db.py,sha256=NcUKn1GF_vteD_GH3daIpOQkbERz_OreiKLfMDu7cjU,4626
|
6
|
+
nomenklatura/delta.py,sha256=4Vp_BbX_Dh1_EFflqiP9ajrLMOGz1NKGV1YWVVROEGo,58
|
7
|
+
nomenklatura/exceptions.py,sha256=Ci-Xu2bXnq6blnNZKw-7ZJT8FzCeW19Zr8bp09LV7uo,179
|
8
|
+
nomenklatura/judgement.py,sha256=trm8_M1a8cannLySc2CH2CS1oxGVtcwVTuwQgW5Mv7k,578
|
9
|
+
nomenklatura/kv.py,sha256=trAQCmFNGDHw_2DsNAlcFakj6Ir4qnpGx6X_VBN2nrw,1079
|
10
|
+
nomenklatura/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
11
|
+
nomenklatura/settings.py,sha256=02RoP1iNgK-BXixNw5-0QHIU_Alc6_oeQXHdyAPO8Pc,595
|
12
|
+
nomenklatura/util.py,sha256=ISa49FV1eov2JLls34UPtaoyx2nX5NvRsW2bLpx8MEs,779
|
13
|
+
nomenklatura/versions.py,sha256=KGiIHS03lQUUHE9iFM_VrmPCXAZlNwk8NK1iRjY5Ulc,3506
|
14
|
+
nomenklatura/xref.py,sha256=UIhtcfIU-8cTvQUeXymPtYOW8EtlSavz_EiNKJ81iNw,4381
|
15
|
+
nomenklatura/data/er-unstable.pkl,sha256=wnZhzaH9hid4gew5Y1fR6gwj5m9Ffs0iHRv-DUOaNcE,2265
|
16
|
+
nomenklatura/data/regression-v1.pkl,sha256=6zt7kqsr2To3nIySqg_zg6r1SZZ8BX2k44OrLAU9hMU,2368
|
17
|
+
nomenklatura/enrich/__init__.py,sha256=AvP25WZFDWs7Uw5sdhZ7Az2AJ8DSgMZDcdwddkxaZ20,3503
|
18
|
+
nomenklatura/enrich/aleph.py,sha256=LmxStxJJYgyzsdZORbqR8M1dDiRI6ESPzDtXlgU0sj0,5682
|
19
|
+
nomenklatura/enrich/common.py,sha256=IDyBio3u9978zGd3046vhwEsRaSyQ0KLcZXRDEfoygc,8181
|
20
|
+
nomenklatura/enrich/nominatim.py,sha256=xeyc290YnWutvUtrgWbB6S7rWYuCIcmmbDy_gkcSxIg,2654
|
21
|
+
nomenklatura/enrich/opencorporates.py,sha256=4nkzMW_IMMI4EDZf9Kpqv0U7nDOJZ5AtwRNgj_gJThc,10213
|
22
|
+
nomenklatura/enrich/openfigi.py,sha256=6KEjcJ21GGAuTJ0NPqTbWmaeR7RrGdiVPmxmV46m7kc,4922
|
23
|
+
nomenklatura/enrich/permid.py,sha256=NTdzdzSHi-w_lFFL9933l1jbRf3o2B8Ffig2aJ8hXXc,8286
|
24
|
+
nomenklatura/enrich/wikidata.py,sha256=BrhpZo9JxHHWX5nZ170u4LGDoUyqYk7_gkc8HLx3-tU,10144
|
25
|
+
nomenklatura/enrich/yente.py,sha256=ynWAIup0pFoURrcTqIXmotWn2vdPSU-NXyHcB-6to2g,4834
|
26
|
+
nomenklatura/index/__init__.py,sha256=XmfiHTWa_6P2FvRPh91y55WTd3kj0I32c_6Ga4zN_us,126
|
27
|
+
nomenklatura/index/common.py,sha256=5Wdy8noLqaurRv8Y5WpCZIWvAyw7iqjwllOEEjCmZG8,687
|
28
|
+
nomenklatura/index/entry.py,sha256=R2h3mbg6U2MqQZV5WkeOeDgJycDI9ymMdzIre0FhEJc,2936
|
29
|
+
nomenklatura/index/index.py,sha256=r6TJn8UqgKTeS6PdBeemZlYzBlfQsR34LgpwTqshyxY,6175
|
30
|
+
nomenklatura/index/tokenizer.py,sha256=od7KTlvTEBB3iFHRu2yVgQZFD6DzvbbWhljl6XUE4qU,3130
|
31
|
+
nomenklatura/matching/__init__.py,sha256=VyJ5U93bg4JoieMg8w3yZZRTxjtsgx25qO7XG3ePxmQ,1487
|
32
|
+
nomenklatura/matching/bench.py,sha256=M0HELVtDa51oCil9sBIHwr2q9cGwaOrWdHlO5OxS6Ck,1058
|
33
|
+
nomenklatura/matching/compat.py,sha256=RWABqEhSHIBQrY99PvK79KcAoetAwiDjDOJQLf5VREQ,2046
|
34
|
+
nomenklatura/matching/pairs.py,sha256=grSTAafaESC6I2Dz6nSp--ws3AL9OrLn0RKWfjQ6TVc,1419
|
35
|
+
nomenklatura/matching/types.py,sha256=r1iJqSIBreukvgBD4kVcqlAImyBY8KkdZnuEVwXppBk,7352
|
36
|
+
nomenklatura/matching/util.py,sha256=z1tExrifx8DbUF81BPm0JpHqfkbhhiUDhXUj4qPh-Lw,2078
|
37
|
+
nomenklatura/matching/compare/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
38
|
+
nomenklatura/matching/compare/addresses.py,sha256=UJlDU5fR5fuBKHCfMCBq_JJmwi7H7_KClH18xmiomcU,3308
|
39
|
+
nomenklatura/matching/compare/countries.py,sha256=8ezqa52fuPJyd3xzVcdyqAme19Q_I2K_Biq2_anrmVs,624
|
40
|
+
nomenklatura/matching/compare/dates.py,sha256=vfF42mwyHnI9m5mzhoUelMRQIHJS1fsnhGbVoOzImig,3668
|
41
|
+
nomenklatura/matching/compare/gender.py,sha256=iQuqXUEaIMRqhDw5p3NzZXX0xghbHrzV2QErMVW0mHM,631
|
42
|
+
nomenklatura/matching/compare/identifiers.py,sha256=ER2uIsll2V-MWlSkTIMDsG_jdbFc6JAjALEhGiqK7PI,1382
|
43
|
+
nomenklatura/matching/compare/names.py,sha256=DHDmOg0CYkwmH0eY1Wcxe2FnjqJC12k0y23EZoZ9bto,6960
|
44
|
+
nomenklatura/matching/compare/util.py,sha256=TfWCfMixO3P6sciqlfn_iI3SPaX_4Jl7qHK_5owLOxk,1427
|
45
|
+
nomenklatura/matching/erun/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
46
|
+
nomenklatura/matching/erun/countries.py,sha256=9PFESV70S5cxcz-J9Nko94JvJcFTrrFy10nOEeMs2S4,1392
|
47
|
+
nomenklatura/matching/erun/identifiers.py,sha256=bh1GetdcrH0hao0YHpAys-arMLNG-LoCmsfsgonTu_4,2289
|
48
|
+
nomenklatura/matching/erun/misc.py,sha256=sq_fAWWbnNEqlUmAQG_2p6heJhts-AmBzEcCL4ah5vc,2446
|
49
|
+
nomenklatura/matching/erun/model.py,sha256=IgQfYHMgqkhkk1Ppw2Sd8KYRqFw2Q2LHOepiVnYXLLM,4330
|
50
|
+
nomenklatura/matching/erun/names.py,sha256=Wl0wqgsW2RkWWJJ14QjCzbtzlr1tRrs_f93PYliCbU8,5081
|
51
|
+
nomenklatura/matching/erun/train.py,sha256=Qg6zHA8u4hfcavJycYbGQ9QZ_BGW4PWmZ3hezkKCeNY,5209
|
52
|
+
nomenklatura/matching/erun/util.py,sha256=KcZwrZCo25rl3LV7kdz3ZrwFK7Gu01XbDbD6tYNV6vo,864
|
53
|
+
nomenklatura/matching/logic_v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
54
|
+
nomenklatura/matching/logic_v1/identifiers.py,sha256=soCJPu2EwaEbJvgHVXiUgfg8rGgoc_cSB-zH33fEFWM,4152
|
55
|
+
nomenklatura/matching/logic_v1/model.py,sha256=UWqdli-HQEYtA0_wUiUO7BkyBdnH-s0NVbxnDi8t0I4,4075
|
56
|
+
nomenklatura/matching/logic_v1/multi.py,sha256=fdyBT89c0KsTtnobS-kPpeP7M15kaXoNwMgXvRHdpwE,917
|
57
|
+
nomenklatura/matching/logic_v1/phonetic.py,sha256=fAVvuLcNrnPc5llLiAiV1pdsIgdtdr3EIZCrozi4HZQ,4932
|
58
|
+
nomenklatura/matching/logic_v2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
59
|
+
nomenklatura/matching/logic_v2/identifiers.py,sha256=cRNnPKrXKc5XG8h00EBaZALIcnnRLbrrHtLDqLh-wgs,4718
|
60
|
+
nomenklatura/matching/logic_v2/model.py,sha256=wSZjlENheSsahqdlsk31Cg96PFnCWtT_rqQFYAQDSQY,4788
|
61
|
+
nomenklatura/matching/logic_v2/names/__init__.py,sha256=PQ_meSq_MYSMZ_6NgLniKPDlJZ3NZZnW8JVgERbNN5w,92
|
62
|
+
nomenklatura/matching/logic_v2/names/analysis.py,sha256=1EPNOSKU_lEOGalsRkTrpUu3DhX5NvKFH3qUaVFZeF8,2264
|
63
|
+
nomenklatura/matching/logic_v2/names/distance.py,sha256=G4q2AeBs009f9uoose06uYnhT_0vneelFusIzS-1NqQ,7005
|
64
|
+
nomenklatura/matching/logic_v2/names/magic.py,sha256=mWAqmMU-eB-Kp-XVNkRSxdECel3j25OiXsESDyqT5ws,2380
|
65
|
+
nomenklatura/matching/logic_v2/names/match.py,sha256=0Vs4j89yx8tOQny2w6gl9Zkf885crOkS6DGl4MSxAUI,9396
|
66
|
+
nomenklatura/matching/logic_v2/names/pairing.py,sha256=bmP3x21zvVTddUKG8HMfLxZ457ItbeO-3wNTrtQ5Ya8,2943
|
67
|
+
nomenklatura/matching/logic_v2/names/util.py,sha256=AHkg9k23O7HSv5uA1TCz-OYE9jlXuNDnCE_IXKltnFI,3061
|
68
|
+
nomenklatura/matching/name_based/__init__.py,sha256=1_CM8vvr1KpTZq-LfK9hU0NPLL4GfVo0KuwG5-Atc7g,186
|
69
|
+
nomenklatura/matching/name_based/misc.py,sha256=Xz7FIIj6Fsg0fshiOQuRw3FqjsnZ7qb7goejUtsFPEI,3951
|
70
|
+
nomenklatura/matching/name_based/model.py,sha256=4VjIml14MWGKUXDll01ewdu5UZrrpatuR6VLXiW9tIU,2418
|
71
|
+
nomenklatura/matching/name_based/names.py,sha256=ghRh5-KxeI6q_4e1vwMz85G8m6eB_LvG6006NDlXRGU,2490
|
72
|
+
nomenklatura/matching/regression_v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
73
|
+
nomenklatura/matching/regression_v1/misc.py,sha256=OKakZQ3rCY0LruuxHqCvsN2L5rBT-ToA6oOyBiAUxuo,2899
|
74
|
+
nomenklatura/matching/regression_v1/model.py,sha256=9yVkLn9AH4fsvd9sAcs84XUA_1MJxsHW_QloFlSL0NY,4421
|
75
|
+
nomenklatura/matching/regression_v1/names.py,sha256=7BIAmzkvs8_ubq69ZBt-RukiM2wAGpFwW6Am1oJE3uM,2417
|
76
|
+
nomenklatura/matching/regression_v1/train.py,sha256=MblkIPNr0dKrEfEUc9CApxVguZXw_z48EXZdvbI-y8c,3568
|
77
|
+
nomenklatura/matching/regression_v1/util.py,sha256=5vCarAj0WtKXdahxTFU8nMoP2bOXYQCmEwnEeAuGegw,893
|
78
|
+
nomenklatura/matching/svm_v1/__init__.py,sha256=8YL0MhfkY2x8SpiCqQXa_OICi72i3E0x3DTAQzSB4p0,112
|
79
|
+
nomenklatura/matching/svm_v1/misc.py,sha256=Qz1vDP9VFCFYGVYekzM4lu83cIWzqxtI4BVsd6M292U,3559
|
80
|
+
nomenklatura/matching/svm_v1/model.py,sha256=1gsMOvSBr7P6M2laOmd9E35N48oSDi5-czsJHps-cDU,6435
|
81
|
+
nomenklatura/matching/svm_v1/names.py,sha256=Spur-fVtmbvsl1xRb_4voKM7ZXpvulS_4_46PHDPq4c,2895
|
82
|
+
nomenklatura/matching/svm_v1/train.py,sha256=Fym3ZwFMDzaPvH6Q5DvZFCmo6ZzaV0HeX6i8ggAqsHs,6768
|
83
|
+
nomenklatura/matching/svm_v1/util.py,sha256=07GB7eISi_o3_7cctM_nY1rYLuCchj4PHeUG8jpY0BM,859
|
84
|
+
nomenklatura/publish/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
85
|
+
nomenklatura/publish/dates.py,sha256=WqTrGg9TWbs_K5E0wc3xL2woPY8EGMzM7bx7HnTl2ko,1805
|
86
|
+
nomenklatura/publish/edges.py,sha256=rXjOW1loNz2ATX6c3dMTSfxpSQZq1VkEYowizHEhhy4,1223
|
87
|
+
nomenklatura/resolver/__init__.py,sha256=etI9g37aYpxZpoESIJYI4T5g7ueU30nryhbh0w7wKU4,292
|
88
|
+
nomenklatura/resolver/common.py,sha256=pJlw-jzw_OGlo6UBYOhhYwICAz_AfzhrOIV0WPdd6X0,46
|
89
|
+
nomenklatura/resolver/edge.py,sha256=Qgvwy4V5Bf8PdVCxkK-1_BvKgkQMdRZnoOU1pKXUgxk,2910
|
90
|
+
nomenklatura/resolver/identifier.py,sha256=B3oR4id1daeQggmPHau1C__0S_lQcr8zDwdna0dYC9c,1613
|
91
|
+
nomenklatura/resolver/linker.py,sha256=LkTDNkjxt5uE2wX-iuOSbFpjFNqeZLRqajhrZ3wFk8s,4019
|
92
|
+
nomenklatura/resolver/resolver.py,sha256=X3HmtjpPm0zCiUvRh4Yho8XimW0-bx0BqLm8T4yu6tg,21733
|
93
|
+
nomenklatura/store/__init__.py,sha256=VvIHv5Y2wM1Zzwml2ttPHk-7-LmuB1LnZgyLOtVTa64,1211
|
94
|
+
nomenklatura/store/base.py,sha256=Dj2KBXJSH-ZUCPIPtzxJn0CRUd3VJ0wfndaU1INRWLE,4419
|
95
|
+
nomenklatura/store/level.py,sha256=vifLdsOcHC_wKfgyUWzBI8oNqEgEz4Opw1AlgPbHVhc,10262
|
96
|
+
nomenklatura/store/memory.py,sha256=x6t4NNKc3wwUrUUEguX4809E1C7MKXNHBJDsOs34Jrg,3997
|
97
|
+
nomenklatura/store/redis_.py,sha256=B7FbdnDXI1BtejkVxuh-IBMZNWJNd8aFYuT5d9wErGQ,4802
|
98
|
+
nomenklatura/store/sql.py,sha256=5pf-_a1B_QkBiJBKJHdam8_NkVnSy3MDU-srQloIvLY,8450
|
99
|
+
nomenklatura/store/util.py,sha256=uigN7G6krca20VuofvQvrkD4akH9Dqe78aeArA6ciyg,1099
|
100
|
+
nomenklatura/store/versioned.py,sha256=ikbog4b4w651fUIo4dNaJZO5ySOoEn_bEMwTw3KKg9M,13819
|
101
|
+
nomenklatura/tui/__init__.py,sha256=fos6Zb6spxpu_ZuQld4qTeL4hzpRyuuOis1FYVWgjsM,435
|
102
|
+
nomenklatura/tui/app.py,sha256=WVb28MJvqECTc6LCnyQlO81PNBj-0Le3WtYQ7CH-QB8,9800
|
103
|
+
nomenklatura/tui/app.tcss,sha256=f_KOAQPI4c1vEUF5KR2Y42nJka6ORvBPq5jmLcrMTNw,660
|
104
|
+
nomenklatura/tui/comparison.py,sha256=7qe70SLWh4QJ1ntlFBNeUcTSurfqSZclbB-9W3X1Av0,2694
|
105
|
+
nomenklatura/tui/util.py,sha256=OIK1ECw2tA7qqObgaaeHydaqLAdc3HAxa8dYW8Z68mI,1091
|
106
|
+
nomenklatura/wikidata/__init__.py,sha256=mVf5Tc_muVzEGcrGUg83GQ9qm1VNlHZQl4RxmBh7bck,379
|
107
|
+
nomenklatura/wikidata/client.py,sha256=bcgr-emOcks3Y0HAcBvqZ2BL0GSGyLwJJJTjBQhgwik,4316
|
108
|
+
nomenklatura/wikidata/lang.py,sha256=2S-0dCd6vJ93d_Vmjbv9joNUnwPlTO9CavF_eAsBy2Y,3089
|
109
|
+
nomenklatura/wikidata/model.py,sha256=W72VcQDhC9jm_QHXKNeRrADoHjwyJIurry394XnsCKg,4654
|
110
|
+
nomenklatura/wikidata/props.py,sha256=7owcZFHK5Fa6kS8fiH-qJ5rorj2XibV62ayX7prZJyI,1701
|
111
|
+
nomenklatura/wikidata/qualified.py,sha256=glH7Oo_QgNG25VGdYqFykz7WIToDsinh7fJEdC4u8gU,1481
|
112
|
+
nomenklatura/wikidata/query.py,sha256=FR012bJPSJ9cdhGId3JoVL3g-VBSzgbvgCIl7Dh5xC8,2189
|
113
|
+
nomenklatura/wikidata/value.py,sha256=CNT5uB5nsHRO1w2gByesGoo6KTss3aild1U8TXLHTSI,2979
|
114
|
+
nomenklatura_mpt-4.1.9.dist-info/METADATA,sha256=mLWEOek4U7w9k8yc7uQuraCYdNAMcrMwcLrHOP1OYz8,8049
|
115
|
+
nomenklatura_mpt-4.1.9.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
116
|
+
nomenklatura_mpt-4.1.9.dist-info/entry_points.txt,sha256=jL6tKzNuFy4t00OWLf66NsLUi070GgfncBhiBsYX5fs,80
|
117
|
+
nomenklatura_mpt-4.1.9.dist-info/licenses/LICENSE,sha256=bAU8lurcfhKXu0FKlBx8gvWWPixioihFCEHRkuBpCQ8,1126
|
118
|
+
nomenklatura_mpt-4.1.9.dist-info/RECORD,,
|
@@ -0,0 +1,21 @@
|
|
1
|
+
Copyright (c) 2013-2022, Friedrich Lindenberg
|
2
|
+
Copyright (c) 2023-2025, OpenSanctions Datenbanken GmbH
|
3
|
+
|
4
|
+
Permission is hereby granted, free of charge, to any person obtaining a
|
5
|
+
copy of this software and associated documentation files (the
|
6
|
+
"Software"), to deal in the Software without restriction, including
|
7
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
8
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
9
|
+
permit persons to whom the Software is furnished to do so, subject to
|
10
|
+
the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included
|
13
|
+
in all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
|
16
|
+
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
17
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
18
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
19
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
20
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
21
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|