ref-id 0.7.0__tar.gz
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.
- ref_id-0.7.0/.gitignore +7 -0
- ref_id-0.7.0/LICENSE +202 -0
- ref_id-0.7.0/PKG-INFO +70 -0
- ref_id-0.7.0/README.md +58 -0
- ref_id-0.7.0/pyproject.toml +36 -0
- ref_id-0.7.0/src/ref_id/__init__.py +69 -0
- ref_id-0.7.0/src/ref_id/build.py +146 -0
- ref_id-0.7.0/src/ref_id/canonical.py +171 -0
- ref_id-0.7.0/src/ref_id/digest.py +45 -0
- ref_id-0.7.0/src/ref_id/encoding.py +78 -0
- ref_id-0.7.0/src/ref_id/envelope.py +64 -0
- ref_id-0.7.0/src/ref_id/errors.py +65 -0
- ref_id-0.7.0/src/ref_id/grammar.py +92 -0
- ref_id-0.7.0/src/ref_id/parse.py +236 -0
- ref_id-0.7.0/src/ref_id/py.typed +0 -0
- ref_id-0.7.0/src/ref_id/relations.py +464 -0
- ref_id-0.7.0/src/ref_id/serialise.py +109 -0
- ref_id-0.7.0/src/ref_id/spec/ref-id.json +5258 -0
- ref_id-0.7.0/src/ref_id/spec/ref-id.json.sha256 +1 -0
- ref_id-0.7.0/src/ref_id/spec.py +192 -0
- ref_id-0.7.0/src/ref_id/types.py +264 -0
- ref_id-0.7.0/src/ref_id/validators.py +258 -0
- ref_id-0.7.0/tests/test_build.py +100 -0
- ref_id-0.7.0/tests/test_canonical.py +109 -0
- ref_id-0.7.0/tests/test_conformance.py +224 -0
- ref_id-0.7.0/tests/test_digest.py +65 -0
- ref_id-0.7.0/tests/test_encoding.py +37 -0
- ref_id-0.7.0/tests/test_envelope.py +43 -0
- ref_id-0.7.0/tests/test_errors.py +32 -0
- ref_id-0.7.0/tests/test_grammar.py +97 -0
- ref_id-0.7.0/tests/test_parse.py +62 -0
- ref_id-0.7.0/tests/test_relations.py +193 -0
- ref_id-0.7.0/tests/test_spec.py +129 -0
- ref_id-0.7.0/tests/test_surface.py +106 -0
- ref_id-0.7.0/tests/test_validators.py +73 -0
- ref_id-0.7.0/tools/parse_lines.py +83 -0
- ref_id-0.7.0/uv.lock +394 -0
ref_id-0.7.0/.gitignore
ADDED
ref_id-0.7.0/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 2026 The ref-id Authors
|
|
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.
|
ref_id-0.7.0/PKG-INFO
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
1
|
+
Metadata-Version: 2.5
|
|
2
|
+
Name: ref-id
|
|
3
|
+
Version: 0.7.0
|
|
4
|
+
Summary: The ref: identifier scheme — a Python port held to the specification's conformance vectors
|
|
5
|
+
Project-URL: Repository, https://github.com/entelekheia-ai/ref-id
|
|
6
|
+
Project-URL: Issues, https://github.com/entelekheia-ai/ref-id/issues
|
|
7
|
+
License-Expression: Apache-2.0
|
|
8
|
+
License-File: LICENSE
|
|
9
|
+
Requires-Python: >=3.11
|
|
10
|
+
Requires-Dist: packageurl-python<0.18,>=0.17.6
|
|
11
|
+
Description-Content-Type: text/markdown
|
|
12
|
+
|
|
13
|
+
# ref-id
|
|
14
|
+
|
|
15
|
+
**The `ref:` identifier scheme, as a Python package held to the specification's conformance vectors.**
|
|
16
|
+
An identifier names a thing by what somebody declared about it — a package, a folder, a domain, a mailbox,
|
|
17
|
+
an agent — never by where a file happens to sit.
|
|
18
|
+
|
|
19
|
+
The specification is data: `ref-id.json` (grammar, tables, digest rules, conformance vectors) ships inside
|
|
20
|
+
the package byte-for-byte and is verified against its digest at load. The package implements the behaviour
|
|
21
|
+
the vectors bind — parse, serialise, build, comparison, digest and the envelope invariant — and restates
|
|
22
|
+
none of the specification's tables. It is one of four implementations of the scheme (TypeScript, Rust,
|
|
23
|
+
Swift, Python) that a differential test holds to the same answers on every input the specification names.
|
|
24
|
+
|
|
25
|
+
## Install
|
|
26
|
+
|
|
27
|
+
```sh
|
|
28
|
+
pip install ref-id
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
Python 3.11 or later. The one dependency is `packageurl-python`, which validates Package URL locators.
|
|
32
|
+
|
|
33
|
+
## Usage
|
|
34
|
+
|
|
35
|
+
Parse an identifier, then re-serialise it. `parse` never raises for an identifier problem: a malformed
|
|
36
|
+
string comes back with `status == "malformed"` and the part that failed; an unknown type comes back
|
|
37
|
+
`uncovered`, carried whole.
|
|
38
|
+
|
|
39
|
+
```python
|
|
40
|
+
import ref_id
|
|
41
|
+
|
|
42
|
+
parsed = ref_id.parse("ref:pkg:npm/@acme/scanner-core@0.1.0#Observation")
|
|
43
|
+
assert parsed.status == "ok"
|
|
44
|
+
assert parsed.type == "pkg"
|
|
45
|
+
assert parsed.delegated == "pkg:npm/@acme/scanner-core@0.1.0"
|
|
46
|
+
assert ref_id.serialise(parsed) == "ref:pkg:npm/@acme/scanner-core@0.1.0#Observation"
|
|
47
|
+
```
|
|
48
|
+
|
|
49
|
+
The other entry points: `build(ref_id.BuildParts(...))` composes an identifier from declared parts and
|
|
50
|
+
refuses what the grammar cannot carry; `digest([...])` hashes an ordered list of identifiers the way the
|
|
51
|
+
specification prescribes; `validate_envelope(requested_id, envelope)` checks a stored record against the
|
|
52
|
+
identifier it was requested under. `covers(general, specific)`, `same_package(a, b)` and
|
|
53
|
+
`same_identifier(a, b)` compare two identifiers — each accepts a `str` or a `ParseResult` — and
|
|
54
|
+
`relate(a, b)` reports the full per-dimension relation the others reduce from, while `verdict(a, b)` reads
|
|
55
|
+
it once location qualifiers are hints: an identity axis, a content axis and what decided each.
|
|
56
|
+
`canonical_identifier` and `canonicalise` produce canonical forms. `load_spec()` returns the embedded
|
|
57
|
+
specification, `load_spec_from(directory)` one read from a directory holding `ref-id.json` and its
|
|
58
|
+
`.sha256` sidecar.
|
|
59
|
+
|
|
60
|
+
Every function but `validate_envelope` takes its arguments by position only, as the specification declares
|
|
61
|
+
them unlabelled. Results are frozen dataclasses; `to_json()` gives the specification's own field names.
|
|
62
|
+
Errors are `RefIdError` and its five kinds.
|
|
63
|
+
|
|
64
|
+
`packageurl-python` decides whether a Package URL locator is valid and how its `canonical` field is spelled,
|
|
65
|
+
and the other implementations use other validators. Where they differ is measured in
|
|
66
|
+
[Known differences between implementations](https://github.com/entelekheia-ai/ref-id/blob/main/docs/reference/implementation-differences.md).
|
|
67
|
+
|
|
68
|
+
## License
|
|
69
|
+
|
|
70
|
+
Apache-2.0. Source, specification and issues: <https://github.com/entelekheia-ai/ref-id>.
|
ref_id-0.7.0/README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
# ref-id
|
|
2
|
+
|
|
3
|
+
**The `ref:` identifier scheme, as a Python package held to the specification's conformance vectors.**
|
|
4
|
+
An identifier names a thing by what somebody declared about it — a package, a folder, a domain, a mailbox,
|
|
5
|
+
an agent — never by where a file happens to sit.
|
|
6
|
+
|
|
7
|
+
The specification is data: `ref-id.json` (grammar, tables, digest rules, conformance vectors) ships inside
|
|
8
|
+
the package byte-for-byte and is verified against its digest at load. The package implements the behaviour
|
|
9
|
+
the vectors bind — parse, serialise, build, comparison, digest and the envelope invariant — and restates
|
|
10
|
+
none of the specification's tables. It is one of four implementations of the scheme (TypeScript, Rust,
|
|
11
|
+
Swift, Python) that a differential test holds to the same answers on every input the specification names.
|
|
12
|
+
|
|
13
|
+
## Install
|
|
14
|
+
|
|
15
|
+
```sh
|
|
16
|
+
pip install ref-id
|
|
17
|
+
```
|
|
18
|
+
|
|
19
|
+
Python 3.11 or later. The one dependency is `packageurl-python`, which validates Package URL locators.
|
|
20
|
+
|
|
21
|
+
## Usage
|
|
22
|
+
|
|
23
|
+
Parse an identifier, then re-serialise it. `parse` never raises for an identifier problem: a malformed
|
|
24
|
+
string comes back with `status == "malformed"` and the part that failed; an unknown type comes back
|
|
25
|
+
`uncovered`, carried whole.
|
|
26
|
+
|
|
27
|
+
```python
|
|
28
|
+
import ref_id
|
|
29
|
+
|
|
30
|
+
parsed = ref_id.parse("ref:pkg:npm/@acme/scanner-core@0.1.0#Observation")
|
|
31
|
+
assert parsed.status == "ok"
|
|
32
|
+
assert parsed.type == "pkg"
|
|
33
|
+
assert parsed.delegated == "pkg:npm/@acme/scanner-core@0.1.0"
|
|
34
|
+
assert ref_id.serialise(parsed) == "ref:pkg:npm/@acme/scanner-core@0.1.0#Observation"
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
The other entry points: `build(ref_id.BuildParts(...))` composes an identifier from declared parts and
|
|
38
|
+
refuses what the grammar cannot carry; `digest([...])` hashes an ordered list of identifiers the way the
|
|
39
|
+
specification prescribes; `validate_envelope(requested_id, envelope)` checks a stored record against the
|
|
40
|
+
identifier it was requested under. `covers(general, specific)`, `same_package(a, b)` and
|
|
41
|
+
`same_identifier(a, b)` compare two identifiers — each accepts a `str` or a `ParseResult` — and
|
|
42
|
+
`relate(a, b)` reports the full per-dimension relation the others reduce from, while `verdict(a, b)` reads
|
|
43
|
+
it once location qualifiers are hints: an identity axis, a content axis and what decided each.
|
|
44
|
+
`canonical_identifier` and `canonicalise` produce canonical forms. `load_spec()` returns the embedded
|
|
45
|
+
specification, `load_spec_from(directory)` one read from a directory holding `ref-id.json` and its
|
|
46
|
+
`.sha256` sidecar.
|
|
47
|
+
|
|
48
|
+
Every function but `validate_envelope` takes its arguments by position only, as the specification declares
|
|
49
|
+
them unlabelled. Results are frozen dataclasses; `to_json()` gives the specification's own field names.
|
|
50
|
+
Errors are `RefIdError` and its five kinds.
|
|
51
|
+
|
|
52
|
+
`packageurl-python` decides whether a Package URL locator is valid and how its `canonical` field is spelled,
|
|
53
|
+
and the other implementations use other validators. Where they differ is measured in
|
|
54
|
+
[Known differences between implementations](https://github.com/entelekheia-ai/ref-id/blob/main/docs/reference/implementation-differences.md).
|
|
55
|
+
|
|
56
|
+
## License
|
|
57
|
+
|
|
58
|
+
Apache-2.0. Source, specification and issues: <https://github.com/entelekheia-ai/ref-id>.
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
[project]
|
|
3
|
+
name = "ref-id"
|
|
4
|
+
version = "0.7.0"
|
|
5
|
+
description = "The ref: identifier scheme — a Python port held to the specification's conformance vectors"
|
|
6
|
+
readme = "README.md"
|
|
7
|
+
license = "Apache-2.0"
|
|
8
|
+
license-files = ["LICENSE"]
|
|
9
|
+
requires-python = ">=3.11"
|
|
10
|
+
dependencies = [
|
|
11
|
+
"packageurl-python>=0.17.6,<0.18",
|
|
12
|
+
]
|
|
13
|
+
|
|
14
|
+
[project.urls]
|
|
15
|
+
Repository = "https://github.com/entelekheia-ai/ref-id"
|
|
16
|
+
Issues = "https://github.com/entelekheia-ai/ref-id/issues"
|
|
17
|
+
|
|
18
|
+
[build-system]
|
|
19
|
+
requires = ["hatchling"]
|
|
20
|
+
build-backend = "hatchling.build"
|
|
21
|
+
|
|
22
|
+
[tool.hatch.build.targets.wheel]
|
|
23
|
+
packages = ["src/ref_id"]
|
|
24
|
+
|
|
25
|
+
[dependency-groups]
|
|
26
|
+
dev = [
|
|
27
|
+
"pytest",
|
|
28
|
+
"mypy",
|
|
29
|
+
"ruff",
|
|
30
|
+
]
|
|
31
|
+
|
|
32
|
+
[tool.mypy]
|
|
33
|
+
strict = true
|
|
34
|
+
|
|
35
|
+
[tool.ruff]
|
|
36
|
+
target-version = "py311"
|
|
@@ -0,0 +1,69 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
"""The `ref:` identifier scheme — a Python port held to `spec/ref-id.json`'s conformance vectors.
|
|
3
|
+
|
|
4
|
+
Track 2 lands the embedded specification, its integrity check, the canonical serialisation and the set
|
|
5
|
+
digest. Parse, serialise, build and the envelope are Track 3; relations are Track 4.
|
|
6
|
+
"""
|
|
7
|
+
from __future__ import annotations
|
|
8
|
+
|
|
9
|
+
from .build import build
|
|
10
|
+
from .canonical import canonicalise
|
|
11
|
+
from .digest import digest
|
|
12
|
+
from .envelope import validate_envelope
|
|
13
|
+
from .errors import (
|
|
14
|
+
BuildError,
|
|
15
|
+
DigestError,
|
|
16
|
+
RefIdError,
|
|
17
|
+
SerialiseError,
|
|
18
|
+
SpecIntegrityError,
|
|
19
|
+
SpecVersionError,
|
|
20
|
+
)
|
|
21
|
+
from .parse import parse
|
|
22
|
+
from .relations import covers, relate, same_identifier, same_package, verdict
|
|
23
|
+
from .serialise import canonical_identifier, serialise
|
|
24
|
+
from .spec import Spec, embedded_spec_text, load_spec, load_spec_from
|
|
25
|
+
from .types import (
|
|
26
|
+
BuildParts,
|
|
27
|
+
EnvelopeResult,
|
|
28
|
+
Fragment,
|
|
29
|
+
NestedValue,
|
|
30
|
+
ParseResult,
|
|
31
|
+
QualifierRelation,
|
|
32
|
+
RelateResult,
|
|
33
|
+
VerdictDecidedBy,
|
|
34
|
+
VerdictResult,
|
|
35
|
+
)
|
|
36
|
+
|
|
37
|
+
__all__ = [
|
|
38
|
+
"BuildError",
|
|
39
|
+
"BuildParts",
|
|
40
|
+
"DigestError",
|
|
41
|
+
"EnvelopeResult",
|
|
42
|
+
"Fragment",
|
|
43
|
+
"NestedValue",
|
|
44
|
+
"ParseResult",
|
|
45
|
+
"QualifierRelation",
|
|
46
|
+
"RefIdError",
|
|
47
|
+
"RelateResult",
|
|
48
|
+
"SerialiseError",
|
|
49
|
+
"Spec",
|
|
50
|
+
"SpecIntegrityError",
|
|
51
|
+
"SpecVersionError",
|
|
52
|
+
"VerdictDecidedBy",
|
|
53
|
+
"VerdictResult",
|
|
54
|
+
"build",
|
|
55
|
+
"canonical_identifier",
|
|
56
|
+
"canonicalise",
|
|
57
|
+
"covers",
|
|
58
|
+
"digest",
|
|
59
|
+
"embedded_spec_text",
|
|
60
|
+
"load_spec",
|
|
61
|
+
"load_spec_from",
|
|
62
|
+
"parse",
|
|
63
|
+
"relate",
|
|
64
|
+
"same_identifier",
|
|
65
|
+
"same_package",
|
|
66
|
+
"serialise",
|
|
67
|
+
"validate_envelope",
|
|
68
|
+
"verdict",
|
|
69
|
+
]
|
|
@@ -0,0 +1,146 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
2
|
+
"""Assembles a `ref:` identifier string from its parts. A part the grammar cannot carry is refused with
|
|
3
|
+
`BuildError` naming it — the builder never emits a string that means something else, which is proven at
|
|
4
|
+
the end by parsing what was built and comparing it with what was asked.
|
|
5
|
+
|
|
6
|
+
Ported from `crates/ref-id/src/build.rs`.
|
|
7
|
+
"""
|
|
8
|
+
from __future__ import annotations
|
|
9
|
+
|
|
10
|
+
from typing import Any
|
|
11
|
+
|
|
12
|
+
from .encoding import contains_any, encode, table_for
|
|
13
|
+
from .errors import BuildError
|
|
14
|
+
from .grammar import (
|
|
15
|
+
FIELD,
|
|
16
|
+
FRAGMENT_INTRODUCER,
|
|
17
|
+
LINE_BREAKS,
|
|
18
|
+
PAIR,
|
|
19
|
+
scheme_prefix,
|
|
20
|
+
)
|
|
21
|
+
from .parse import parse
|
|
22
|
+
from .spec import Spec, load_spec
|
|
23
|
+
from .types import BuildParts, Fragment, NestedValue
|
|
24
|
+
from .validators import folds_type
|
|
25
|
+
|
|
26
|
+
__all__ = ["build"]
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
def _nesting_form(spec: Spec, key: str) -> dict[str, Any] | None:
|
|
30
|
+
declared = spec.get_object("qualifiers")
|
|
31
|
+
entry = declared.get(key) if declared is not None else None
|
|
32
|
+
if not isinstance(entry, dict):
|
|
33
|
+
return None
|
|
34
|
+
forms = spec.get_object("forms") or {}
|
|
35
|
+
for name in entry.get("forms", []):
|
|
36
|
+
if not isinstance(name, str):
|
|
37
|
+
continue
|
|
38
|
+
form = forms.get(name)
|
|
39
|
+
if isinstance(form, dict) and form.get("nested") is True:
|
|
40
|
+
return form
|
|
41
|
+
return None
|
|
42
|
+
|
|
43
|
+
|
|
44
|
+
def _refuse(spec: Spec, part: str, why: str) -> BuildError:
|
|
45
|
+
return _refuse_at(spec.part(part), why)
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
def _refuse_at(part: str, why: str) -> BuildError:
|
|
49
|
+
"""The message names the refused part, so a caller reads what to change instead of guessing and
|
|
50
|
+
retrying. A part `parse` already reported is used verbatim: it may be a key the identifier carries
|
|
51
|
+
and the spec never declared."""
|
|
52
|
+
return BuildError(part, f"cannot build: {why} — refused at the {part}")
|
|
53
|
+
|
|
54
|
+
|
|
55
|
+
def build(parts: BuildParts, /) -> str:
|
|
56
|
+
"""Builds a `ref:` identifier string."""
|
|
57
|
+
spec = load_spec()
|
|
58
|
+
grammar = spec.grammar()
|
|
59
|
+
state_separator = spec.get_str("grammar", "state", "separator")
|
|
60
|
+
fragment_separator = spec.get_str("grammar", "fragment", "separator")
|
|
61
|
+
separators = state_separator + FRAGMENT_INTRODUCER + "".join(LINE_BREAKS)
|
|
62
|
+
fragment_reserved = fragment_separator + "".join(LINE_BREAKS)
|
|
63
|
+
|
|
64
|
+
locator = parts.locator
|
|
65
|
+
fold = f"{parts.type}{FIELD}"
|
|
66
|
+
if folds_type(spec, parts.type) and locator.startswith(fold):
|
|
67
|
+
locator = locator[len(fold) :]
|
|
68
|
+
|
|
69
|
+
if not locator or contains_any(locator, separators):
|
|
70
|
+
raise _refuse(spec, "locator", "a locator is handed to its validator verbatim and cannot carry a reserved character")
|
|
71
|
+
|
|
72
|
+
out = [f"{scheme_prefix(spec)}{parts.type}{FIELD}{locator}"]
|
|
73
|
+
|
|
74
|
+
if parts.qualifiers:
|
|
75
|
+
rendered = []
|
|
76
|
+
for pair in parts.qualifiers:
|
|
77
|
+
# `parts.qualifiers` is declared as a tuple of `(key, value)` pairs; a caller who hands a
|
|
78
|
+
# `dict` instead bypasses the type checker (as `BuildParts.from_json`'s own malformed-shape
|
|
79
|
+
# guard already does for the JSON entry point) and would otherwise unpack each dict *key*
|
|
80
|
+
# string into `key, value` — silently wrong for a two-character key, a bare `ValueError` for
|
|
81
|
+
# any other length. Checked and refused here the same way `from_json` refuses its own shape.
|
|
82
|
+
if not isinstance(pair, (tuple, list)) or len(pair) != 2 or not isinstance(pair[0], str):
|
|
83
|
+
raise _refuse(spec, "state", "a qualifier is a (key, value) pair with a string key")
|
|
84
|
+
key, value = pair
|
|
85
|
+
if isinstance(value, NestedValue):
|
|
86
|
+
if not isinstance(value.nested, str):
|
|
87
|
+
raise _refuse(spec, key, "a qualifier value is a string or NestedValue holding a string")
|
|
88
|
+
form = _nesting_form(spec, key)
|
|
89
|
+
if form is None:
|
|
90
|
+
raise _refuse(spec, key, "this qualifier declares no nesting form")
|
|
91
|
+
encoded = encode(value.nested, table_for(spec, form))
|
|
92
|
+
elif isinstance(value, str):
|
|
93
|
+
if value.startswith(scheme_prefix(spec)) or contains_any(value, separators):
|
|
94
|
+
raise _refuse(spec, key, "a nested identifier is passed as Nested, never as a plain string")
|
|
95
|
+
encoded = value
|
|
96
|
+
else:
|
|
97
|
+
raise _refuse(spec, key, "a qualifier value is a string or NestedValue holding a string")
|
|
98
|
+
rendering = f"{key}{PAIR}{encoded}"
|
|
99
|
+
if grammar.state_pair.fullmatch(rendering) is None:
|
|
100
|
+
raise _refuse(spec, key, "the key does not fit the pair grammar")
|
|
101
|
+
rendered.append(rendering)
|
|
102
|
+
out.append(state_separator)
|
|
103
|
+
out.append(state_separator.join(rendered))
|
|
104
|
+
|
|
105
|
+
wanted_path: str | None = None
|
|
106
|
+
wanted_refinements: tuple[tuple[str, str], ...] = ()
|
|
107
|
+
if parts.fragment is not None:
|
|
108
|
+
if isinstance(parts.fragment, str):
|
|
109
|
+
path = parts.fragment
|
|
110
|
+
elif isinstance(parts.fragment, Fragment):
|
|
111
|
+
path = parts.fragment.path
|
|
112
|
+
wanted_refinements = parts.fragment.refinements
|
|
113
|
+
else:
|
|
114
|
+
raise _refuse(spec, "fragment", "a fragment is a string or Fragment")
|
|
115
|
+
if not path or contains_any(path, fragment_reserved):
|
|
116
|
+
raise _refuse(spec, "fragment", "a declared-name path cannot be empty or carry the refinement separator")
|
|
117
|
+
for key, value in wanted_refinements:
|
|
118
|
+
if contains_any(value, fragment_reserved):
|
|
119
|
+
raise _refuse(spec, key, "a refinement value cannot carry the separator")
|
|
120
|
+
out.append(FRAGMENT_INTRODUCER)
|
|
121
|
+
out.append(path)
|
|
122
|
+
if wanted_refinements:
|
|
123
|
+
out.append(fragment_separator)
|
|
124
|
+
out.append(fragment_separator.join(f"{key}{PAIR}{value}" for key, value in wanted_refinements))
|
|
125
|
+
wanted_path = path
|
|
126
|
+
|
|
127
|
+
assembled = "".join(out)
|
|
128
|
+
|
|
129
|
+
# The last word is the grammar's: what was built must decompose to exactly what was asked.
|
|
130
|
+
if grammar.top.fullmatch(assembled) is None:
|
|
131
|
+
raise _refuse(spec, "grammar", "the assembled string does not match the grammar")
|
|
132
|
+
check = parse(assembled)
|
|
133
|
+
if check.status == spec.status("malformed"):
|
|
134
|
+
refused = check.part if check.part is not None else spec.part("grammar")
|
|
135
|
+
raise _refuse_at(refused, "the assembled string is malformed")
|
|
136
|
+
if check.explicit_version or check.type != parts.type:
|
|
137
|
+
raise _refuse(spec, "type", "the type re-split into other parts")
|
|
138
|
+
if check.locator != locator:
|
|
139
|
+
raise _refuse(spec, "locator", "the locator re-split into other parts")
|
|
140
|
+
if len(check.qualifiers) != len(parts.qualifiers):
|
|
141
|
+
raise _refuse(spec, "state", "a qualifier re-split into other parts")
|
|
142
|
+
check_path = check.fragment.path if check.fragment is not None else None
|
|
143
|
+
check_refinements = len(check.fragment.refinements) if check.fragment is not None else 0
|
|
144
|
+
if check_path != wanted_path or check_refinements != len(wanted_refinements):
|
|
145
|
+
raise _refuse(spec, "fragment", "the fragment re-split into other parts")
|
|
146
|
+
return assembled
|