cmem-plugin-graphsigning 0.5.0__tar.gz

cmem_plugin_graphsigning-0.5.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright eccenca GmbH
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cmem_plugin_graphsigning-0.5.0/PKG-INFO

@@ -0,0 +1,50 @@
+Metadata-Version: 2.4
+Name: cmem-plugin-graphsigning
+Version: 0.5.0
+Summary: Compute hashes and signatures over Knowledge Graphs.
+License: Apache-2.0
+License-File: LICENSE
+Keywords: eccenca Corporate Memory,plugin
+Author: eccenca GmbH
+Author-email: cmempy-developer@eccenca.com
+Requires-Python: >=3.13,<4.0
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Plugins
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Requires-Dist: cmem-client (>=1.0.0,<2.0.0)
+Requires-Dist: cmem-plugin-base (>=4.20.0,<5.0.0)
+Requires-Dist: cryptography (>=50.0.0,<51.0.0)
+Requires-Dist: pyoxigraph (>=0.5.11,<0.6.0)
+Requires-Dist: rdflib (>=7.6.0,<8.0.0)
+Description-Content-Type: text/markdown
+
+# cmem-plugin-graphsigning
+
+Compute hashes and signatures over Knowledge Graphs.
+
+[![eccenca Corporate Memory][cmem-shield]][cmem-link]
+
+This is a plugin for [eccenca Corporate Memory](https://documentation.eccenca.com). You can install it with the [cmemc](https://eccenca.com/go/cmemc) command line client like this:
+
+```
+cmemc admin workspace python install cmem-plugin-graphsigning
+```
+ [![pypi version](https://img.shields.io/pypi/v/cmem-plugin-graphsigning)](https://pypi.org/project/cmem-plugin-graphsigning) [![license](https://img.shields.io/pypi/l/cmem-plugin-graphsigning)](https://pypi.org/project/cmem-plugin-graphsigning)
+[![poetry][poetry-shield]][poetry-link] [![ruff][ruff-shield]][ruff-link] [![mypy][mypy-shield]][mypy-link] [![copier][copier-shield]][copier] 
+
+[cmem-link]: https://documentation.eccenca.com
+[cmem-shield]: https://img.shields.io/endpoint?url=https://documentation.eccenca.com/latest/badge.json
+[poetry-link]: https://python-poetry.org/
+[poetry-shield]: https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json
+[ruff-link]: https://docs.astral.sh/ruff/
+[ruff-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json&label=Code%20Style
+[mypy-link]: https://mypy-lang.org/
+[mypy-shield]: https://www.mypy-lang.org/static/mypy_badge.svg
+[copier]: https://copier.readthedocs.io/
+[copier-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/copier-org/copier/master/img/badge/badge-grayscale-inverted-border-purple.json
+
+

cmem_plugin_graphsigning-0.5.0/README-public.md

@@ -0,0 +1,25 @@
+# cmem-plugin-graphsigning
+
+Compute hashes and signatures over Knowledge Graphs.
+
+[![eccenca Corporate Memory][cmem-shield]][cmem-link]
+
+This is a plugin for [eccenca Corporate Memory](https://documentation.eccenca.com). You can install it with the [cmemc](https://eccenca.com/go/cmemc) command line client like this:
+
+```
+cmemc admin workspace python install cmem-plugin-graphsigning
+```
+ [![pypi version](https://img.shields.io/pypi/v/cmem-plugin-graphsigning)](https://pypi.org/project/cmem-plugin-graphsigning) [![license](https://img.shields.io/pypi/l/cmem-plugin-graphsigning)](https://pypi.org/project/cmem-plugin-graphsigning)
+[![poetry][poetry-shield]][poetry-link] [![ruff][ruff-shield]][ruff-link] [![mypy][mypy-shield]][mypy-link] [![copier][copier-shield]][copier] 
+
+[cmem-link]: https://documentation.eccenca.com
+[cmem-shield]: https://img.shields.io/endpoint?url=https://documentation.eccenca.com/latest/badge.json
+[poetry-link]: https://python-poetry.org/
+[poetry-shield]: https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json
+[ruff-link]: https://docs.astral.sh/ruff/
+[ruff-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json&label=Code%20Style
+[mypy-link]: https://mypy-lang.org/
+[mypy-shield]: https://www.mypy-lang.org/static/mypy_badge.svg
+[copier]: https://copier.readthedocs.io/
+[copier-shield]: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/copier-org/copier/master/img/badge/badge-grayscale-inverted-border-purple.json
+

cmem_plugin_graphsigning-0.5.0/cmem_plugin_graphsigning/__init__.py

@@ -0,0 +1 @@
+"""cmem-plugin-graphsigning"""

cmem_plugin_graphsigning-0.5.0/cmem_plugin_graphsigning/canonicalization.py

@@ -0,0 +1,173 @@
+"""RDFC-1.0 canonicalization, delegated to pyoxigraph rather than hand-rolled.
+
+Canonicalizing a blank-node-heavy graph correctly - assigning the one blank node
+labelling the algorithm defines as canonical, not merely *a* consistent one - is
+notoriously easy to get subtly wrong, and worst-case exponential in the number of
+blank nodes by the algorithm's own design. pyoxigraph implements RDFC-1.0 against
+the official W3C test suite, so this module leans on it rather than maintaining a
+from-scratch canonicalizer.
+
+Canonicalization runs in a throwaway subprocess so a graph shaped to blow up the
+algorithm's worst case can be killed outright once it exceeds the time budget - a
+plain thread or signal-based timeout cannot interrupt a blocking native call like
+this one.
+"""
+
+import hashlib
+import multiprocessing as mp
+import multiprocessing.connection
+from dataclasses import dataclass
+
+import pyoxigraph as ox
+import rdflib
+
+DEFAULT_TIMEOUT_SECONDS = 5.0
+
+
+class CanonicalizationTimeoutError(TimeoutError):
+    """Raised when canonicalizing a graph exceeds its time budget.
+
+    RDFC-1.0's blank node labelling algorithm is worst-case exponential in the
+    number of blank nodes by design, so a graph shaped adversarially - or just
+    unusually blank-node-heavy - can be made to run arbitrarily long; this is a
+    property of the algorithm itself; not a bug either here or in pyoxigraph.
+    """
+
+    def __init__(self, timeout: float) -> None:
+        super().__init__(
+            f"Canonicalization exceeded {timeout}s. A graph with many blank nodes "
+            f"that hash alike can make RDFC-1.0's worst case exponential; this is "
+            f"inherent to the algorithm, not a bug."
+        )
+
+
+class CanonicalizationError(ValueError):
+    """Raised when *nquads* could not be parsed and canonicalized."""
+
+
+@dataclass(frozen=True)
+class _WorkerFailure:
+    """A worker-side exception, carried back to the parent as data.
+
+    The original exception's class may not exist in the parent's import path in
+    every case (pyoxigraph's own exception types, for instance), so only its
+    message crosses the process boundary - re-raised here as a plain ValueError
+    rather than something that could fail to unpickle.
+    """
+
+    message: str
+
+
+def _canonicalize_worker(
+    nquads: bytes, connection: "mp.connection.Connection[bytes | _WorkerFailure, object]"
+) -> None:
+    """Parse, canonicalize and serialize *nquads* in a worker process.
+
+    Runs entirely inside the subprocess so the only thing crossing back to the
+    parent is the finished result - never a live pyoxigraph object, which would
+    not survive the process boundary regardless. Only the failures input can cause
+    are sent back with their reason; anything else ends the worker, and the parent
+    reports a worker that exits without a result.
+    """
+    try:
+        dataset = ox.Dataset()
+        for quad in ox.parse(input=nquads, format=ox.RdfFormat.N_QUADS):
+            dataset.add(quad)
+        dataset.canonicalize(ox.CanonicalizationAlgorithm.RDFC_1_0)
+        serialized = ox.serialize(list(dataset), format=ox.RdfFormat.N_QUADS) or b""
+        lines = sorted(serialized.decode("utf-8").splitlines())
+        result: bytes | _WorkerFailure = ("\n".join(lines) + "\n").encode("utf-8") if lines else b""
+    except (SyntaxError, ValueError) as error:
+        result = _WorkerFailure(f"{type(error).__name__}: {error}")
+    connection.send(result)
+    connection.close()
+
+
+def canonicalize_nquads(nquads: bytes, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> bytes:
+    """Return *nquads* in RDFC-1.0 canonical form: sorted, newline-terminated N-Quads.
+
+    Runs in a fresh ``spawn``-started subprocess, killed outright if it does not
+    finish within *timeout* seconds - the only way to bound a blocking native call
+    that does not check back in with Python for a cooperative cancellation.
+
+    The parent waits for the result and for the worker's exit together. Waiting for
+    the exit alone would never end for a result larger than the pipe holds, since the
+    worker cannot finish sending it until the parent starts reading; waiting for the
+    result alone would never end for a worker that died without sending one.
+    """
+    ctx = mp.get_context("spawn")
+    receiver, sender = ctx.Pipe(duplex=False)
+    process = ctx.Process(target=_canonicalize_worker, args=(nquads, sender))
+    process.start()
+    sender.close()
+    try:
+        ready = mp.connection.wait([receiver, process.sentinel], timeout)
+        if not ready:
+            raise CanonicalizationTimeoutError(timeout)
+        try:
+            result = receiver.recv()
+        except EOFError:
+            process.join()
+            raise CanonicalizationError(
+                f"Canonicalization ended without a result (exit code {process.exitcode})"
+            ) from None
+    finally:
+        receiver.close()
+        if process.is_alive():
+            process.kill()
+        process.join()
+    if isinstance(result, _WorkerFailure):
+        raise CanonicalizationError(f"Failed to canonicalize RDF: {result.message}")
+    return bytes(result)
+
+
+def canonical_digest_bytes(nquads: bytes, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> bytes:
+    """Return the SHA-256 digest of *nquads* in its RDFC-1.0 canonical form.
+
+    **This hash is a security use**: every digest a signature is made over goes
+    through here.
+    """
+    return hashlib.sha256(canonicalize_nquads(nquads, timeout=timeout)).digest()
+
+
+def _as_rdflib_term(term: ox.NamedNode | ox.BlankNode | ox.Literal) -> rdflib.term.Node:
+    """Translate one pyoxigraph term into the equivalent rdflib term, without normalizing it."""
+    if isinstance(term, ox.Literal):
+        language = term.language
+        return rdflib.Literal(
+            term.value,
+            lang=language,
+            datatype=None if language else rdflib.URIRef(term.datatype.value),
+            normalize=False,
+        )
+    if isinstance(term, ox.BlankNode):
+        return rdflib.BNode(term.value)
+    return rdflib.URIRef(term.value)
+
+
+def parse_without_normalizing(
+    data: bytes, rdf_format: ox.RdfFormat = ox.RdfFormat.N_QUADS
+) -> rdflib.Graph:
+    """Parse *data* into an rdflib.Graph without rewriting any literal's lexical form.
+
+    rdflib's own parser rewrites a recognized datatype's lexical form the moment it
+    constructs a Literal - an ``xsd:dateTime`` written ``...Z`` comes back ``...+00:00`` -
+    governed by a process-global flag (``rdflib.NORMALIZE_LITERALS``) this plugin must
+    never touch: Corporate Memory's DataIntegration runs every installed plugin in one
+    shared, concurrently-executing Python interpreter, so a global flip here would leak
+    into every other plugin sharing that process, or race against one running at the
+    same time. Parsing through pyoxigraph instead - which never rewrites a literal - and
+    translating its terms into rdflib's own term types (each ``Literal`` built with
+    ``normalize=False``, a per-instance argument rather than shared state) reads the same
+    bytes into the same graph structure without that side effect.
+    """
+    graph = rdflib.Graph()
+    for quad in ox.parse(input=data, format=rdf_format):
+        graph.add(
+            (
+                _as_rdflib_term(quad.subject),
+                _as_rdflib_term(quad.predicate),
+                _as_rdflib_term(quad.object),
+            )
+        )
+    return graph