subschema 0.0.1__tar.gz

subschema-0.0.1/.gitignore

@@ -0,0 +1,28 @@
+# Python
+__pycache__/
+*.py[cod]
+*.pyo
+*.pyd
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+.coverage
+htmlcov/
+
+# Virtual environments
+.venv/
+.venv-*/
+
+# Packaging
+build/
+dist/
+*.egg-info/
+
+# Local/editor files
+.vscode/
+.DS_Store
+
+# Project-local generated files
+PLAN.md
+sbom.json
+examples/

subschema-0.0.1/LICENSE

@@ -0,0 +1,177 @@
+
+                                 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

subschema-0.0.1/PKG-INFO

@@ -0,0 +1,102 @@
+Metadata-Version: 2.4
+Name: subschema
+Version: 0.0.1
+Summary: A conservative JSON Schema subschema prover
+Project-URL: Homepage, https://github.com/ArakawaHenri/subschema
+Project-URL: Repository, https://github.com/ArakawaHenri/subschema
+Author-email: Henri <henri-zhang@outlook.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Python: >=3.12
+Requires-Dist: greenery>=4.0.0
+Requires-Dist: jsonschema
+Requires-Dist: jsonschema-rs>=0.46.5
+Requires-Dist: referencing
+Requires-Dist: z3-solver
+Description-Content-Type: text/markdown
+
+# subschema
+
+`subschema` is a conservative prover for JSON Schema subschema checks.
+
+For JSON Schemas `lhs` and `rhs`, `lhs <: rhs` means every JSON instance that
+validates against `lhs` also validates against `rhs`.
+
+The PyPI package, Python import package, and CLI command are named `subschema`.
+
+## Install
+
+```bash
+pip install subschema
+```
+
+For local development:
+
+```bash
+uv sync --locked --group dev
+uv run pytest -q
+uv run ruff check .
+```
+
+## CLI
+
+```bash
+subschema lhs.json rhs.json
+```
+
+The command prints whether `lhs.json <: rhs.json`.
+
+Finite expensive proof products can be enabled explicitly:
+
+```bash
+subschema --endeavor --max-work 20000 --timeout-ms 3000 lhs.json rhs.json
+```
+
+`max_work` and `timeout_ms` are only accepted with `--endeavor`. A value of `-1`
+means unlimited for that control.
+
+## Python API
+
+```python
+from subschema import Dialect, is_subschema
+
+lhs = {"type": "integer"}
+rhs = {"type": "number"}
+
+print(is_subschema(lhs, rhs, dialect=Dialect.DRAFT202012))
+```
+
+Available public entrypoints:
+
+- `is_subschema(lhs, rhs, *, dialect=None, proof_options=None, endeavor=False, max_work=None, timeout_ms=None)`
+- `is_equivalent(lhs, rhs, *, dialect=None, proof_options=None, endeavor=False, max_work=None, timeout_ms=None)`
+- `meet_schemas(lhs, rhs, *, dialect=None, proof_options=None, endeavor=False, max_work=None, timeout_ms=None)`
+- `join_schemas(lhs, rhs, *, dialect=None, proof_options=None, endeavor=False, max_work=None, timeout_ms=None)`
+- `canonicalize_schema(schema, *, dialect=None)`
+
+## Dialects
+
+Draft 2020-12 is the default dialect for calls without an explicit dialect or
+`$schema` declaration. Older dialects can be selected by passing `dialect=...`
+or by using a `$schema` declaration.
+
+Supported dialects:
+
+- Draft 4
+- Draft 6
+- Draft 7
+- Draft 2019-09
+- Draft 2020-12
+
+The prover is intentionally conservative. Unsupported, unbounded, recursive, or
+exhausted proof fragments are reported instead of being silently approximated.
+
+## Acknowledgement
+
+This project is a rewrite based on IBM's
+[jsonsubschema](https://github.com/IBM/jsonsubschema) project and may retain
+portions of its source code. Credit to IBM and contributors.
+
+## License
+
+Apache License 2.0. See [LICENSE](LICENSE).

subschema-0.0.1/README.md

@@ -0,0 +1,85 @@
+# subschema
+
+`subschema` is a conservative prover for JSON Schema subschema checks.
+
+For JSON Schemas `lhs` and `rhs`, `lhs <: rhs` means every JSON instance that
+validates against `lhs` also validates against `rhs`.
+
+The PyPI package, Python import package, and CLI command are named `subschema`.
+
+## Install
+
+```bash
+pip install subschema
+```
+
+For local development:
+
+```bash
+uv sync --locked --group dev
+uv run pytest -q
+uv run ruff check .
+```
+
+## CLI
+
+```bash
+subschema lhs.json rhs.json
+```
+
+The command prints whether `lhs.json <: rhs.json`.
+
+Finite expensive proof products can be enabled explicitly:
+
+```bash
+subschema --endeavor --max-work 20000 --timeout-ms 3000 lhs.json rhs.json
+```
+
+`max_work` and `timeout_ms` are only accepted with `--endeavor`. A value of `-1`
+means unlimited for that control.
+
+## Python API
+
+```python
+from subschema import Dialect, is_subschema
+
+lhs = {"type": "integer"}
+rhs = {"type": "number"}
+
+print(is_subschema(lhs, rhs, dialect=Dialect.DRAFT202012))
+```
+
+Available public entrypoints:
+
+- `is_subschema(lhs, rhs, *, dialect=None, proof_options=None, endeavor=False, max_work=None, timeout_ms=None)`
+- `is_equivalent(lhs, rhs, *, dialect=None, proof_options=None, endeavor=False, max_work=None, timeout_ms=None)`
+- `meet_schemas(lhs, rhs, *, dialect=None, proof_options=None, endeavor=False, max_work=None, timeout_ms=None)`
+- `join_schemas(lhs, rhs, *, dialect=None, proof_options=None, endeavor=False, max_work=None, timeout_ms=None)`
+- `canonicalize_schema(schema, *, dialect=None)`
+
+## Dialects
+
+Draft 2020-12 is the default dialect for calls without an explicit dialect or
+`$schema` declaration. Older dialects can be selected by passing `dialect=...`
+or by using a `$schema` declaration.
+
+Supported dialects:
+
+- Draft 4
+- Draft 6
+- Draft 7
+- Draft 2019-09
+- Draft 2020-12
+
+The prover is intentionally conservative. Unsupported, unbounded, recursive, or
+exhausted proof fragments are reported instead of being silently approximated.
+
+## Acknowledgement
+
+This project is a rewrite based on IBM's
+[jsonsubschema](https://github.com/IBM/jsonsubschema) project and may retain
+portions of its source code. Credit to IBM and contributors.
+
+## License
+
+Apache License 2.0. See [LICENSE](LICENSE).

subschema-0.0.1/pyproject.toml

@@ -0,0 +1,76 @@
+[build-system]
+requires = ["hatchling>=1.30.1"]
+build-backend = "hatchling.build"
+
+[project]
+name = "subschema"
+version = "0.0.1"
+description = "A conservative JSON Schema subschema prover"
+readme = "README.md"
+requires-python = ">=3.12"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [
+    { name = "Henri", email = "henri-zhang@outlook.com" },
+]
+dependencies = [
+    "greenery>=4.0.0",
+    "jsonschema",
+    "jsonschema-rs>=0.46.5",
+    "referencing",
+    "z3-solver",
+]
+
+[project.urls]
+Homepage = "https://github.com/ArakawaHenri/subschema"
+Repository = "https://github.com/ArakawaHenri/subschema"
+
+[project.scripts]
+subschema = "subschema.cli:main"
+
+[tool.hatch.build.targets.wheel]
+only-include = ["src"]
+sources = ["src"]
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "src",
+    "LICENSE",
+    "README.md",
+    "pyproject.toml",
+    "uv.lock",
+]
+
+[dependency-groups]
+dev = [
+    "coverage[toml]",
+    "pytest",
+    "ruff",
+]
+security = [
+    "cyclonedx-bom>=4.1.0",
+    "pip-audit>=2.8.0",
+]
+
+[tool.ruff]
+target-version = "py312"
+line-length = 88
+
+[tool.ruff.lint]
+select = [
+    "C4",
+    "E",
+    "F401",
+    "F841",
+    "I",
+    "N",
+    "PERF401",
+    "RET504",
+    "RET505",
+    "SIM118",
+    "UP",
+    "W605",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"test/**/*.py" = ["E", "I", "N", "W"]

subschema-0.0.1/src/subschema/__init__.py

@@ -0,0 +1,19 @@
+from subschema import api, exceptions
+from subschema.dialects import Dialect
+
+is_subschema = api.is_subschema
+meet_schemas = api.meet_schemas
+join_schemas = api.join_schemas
+is_equivalent = api.is_equivalent
+
+canonicalize_schema = api.canonicalize_schema
+
+__all__ = [
+    "Dialect",
+    "canonicalize_schema",
+    "exceptions",
+    "is_equivalent",
+    "is_subschema",
+    "join_schemas",
+    "meet_schemas",
+]

subschema-0.0.1/src/subschema/api.py

@@ -0,0 +1,172 @@
+"""
+Public API entrypoints.
+"""
+
+from copy import deepcopy
+
+from subschema.dialects import (
+    resolve_dialect,
+    strip_inactive_keywords_for_dialect,
+    validate_supported_keywords,
+)
+from subschema.kernel.contracts import ProofBudgets, ProofOptions
+from subschema.kernel.engine import ProofEngine
+from subschema.kernel.json_data import ensure_json_value
+from subschema.kernel.normalization import normalize_boolean_schemas
+from subschema.kernel.validation import validate_raw_schema_for_dialect
+
+
+def canonicalize_schema(s, *, dialect=None):
+    """Return a modern normalized schema without embedding removed checker objects."""
+    ensure_json_value(s, label="schema")
+    resolved_dialect = resolve_dialect(s, dialect=dialect)
+    _validate_public_schema(s, resolved_dialect)
+    schema = strip_inactive_keywords_for_dialect(
+        normalize_boolean_schemas(deepcopy(s)), resolved_dialect
+    )
+    validate_supported_keywords(schema, resolved_dialect)
+    return schema
+
+
+def _validate_public_schema(schema, dialect):
+    stripped = strip_inactive_keywords_for_dialect(schema, dialect)
+    validate_raw_schema_for_dialect(stripped, dialect)
+
+
+def _resolve_proof_options(
+    proof_options=None,
+    *,
+    endeavor=False,
+    max_work=None,
+    timeout_ms=None,
+):
+    if not isinstance(endeavor, bool):
+        raise TypeError("endeavor must be a boolean")
+    if proof_options is not None:
+        if not isinstance(proof_options, ProofOptions):
+            raise TypeError("proof_options must be a ProofOptions instance")
+        if endeavor or max_work is not None or timeout_ms is not None:
+            raise ValueError(
+                "proof_options cannot be combined with endeavor, max_work, or "
+                "timeout_ms"
+            )
+        return proof_options
+    if (max_work is not None or timeout_ms is not None) and not endeavor:
+        raise ValueError("max_work and timeout_ms require endeavor=True")
+    if endeavor:
+        return ProofOptions(
+            endeavor=endeavor,
+            budgets=ProofBudgets(
+                max_work=4096 if max_work is None else max_work,
+                timeout_ms=1000 if timeout_ms is None else timeout_ms,
+            ),
+        )
+    return None
+
+
+def is_subschema(
+    s1,
+    s2,
+    *,
+    dialect=None,
+    proof_options=None,
+    endeavor=False,
+    max_work=None,
+    timeout_ms=None,
+):
+    """Entry point for schema subtype checking."""
+    ensure_json_value(s1, label="lhs schema")
+    ensure_json_value(s2, label="rhs schema")
+    resolved_dialect = resolve_dialect(s1, s2, dialect=dialect)
+    _validate_public_schema(s1, resolved_dialect)
+    _validate_public_schema(s2, resolved_dialect)
+    options = _resolve_proof_options(
+        proof_options,
+        endeavor=endeavor,
+        max_work=max_work,
+        timeout_ms=timeout_ms,
+    )
+    return ProofEngine.for_schemas(
+        s1, s2, dialect=resolved_dialect, options=options
+    ).is_subschema_bool(s1, s2)
+
+
+def meet_schemas(
+    s1,
+    s2,
+    *,
+    dialect=None,
+    proof_options=None,
+    endeavor=False,
+    max_work=None,
+    timeout_ms=None,
+):
+    """Entry point for schema meet operation."""
+    ensure_json_value(s1, label="lhs schema")
+    ensure_json_value(s2, label="rhs schema")
+    resolved_dialect = resolve_dialect(s1, s2, dialect=dialect)
+    _validate_public_schema(s1, resolved_dialect)
+    _validate_public_schema(s2, resolved_dialect)
+    options = _resolve_proof_options(
+        proof_options,
+        endeavor=endeavor,
+        max_work=max_work,
+        timeout_ms=timeout_ms,
+    )
+    return ProofEngine.for_schemas(
+        s1, s2, dialect=resolved_dialect, options=options
+    ).meet(s1, s2)
+
+
+def join_schemas(
+    s1,
+    s2,
+    *,
+    dialect=None,
+    proof_options=None,
+    endeavor=False,
+    max_work=None,
+    timeout_ms=None,
+):
+    """Entry point for schema join operation."""
+    ensure_json_value(s1, label="lhs schema")
+    ensure_json_value(s2, label="rhs schema")
+    resolved_dialect = resolve_dialect(s1, s2, dialect=dialect)
+    _validate_public_schema(s1, resolved_dialect)
+    _validate_public_schema(s2, resolved_dialect)
+    options = _resolve_proof_options(
+        proof_options,
+        endeavor=endeavor,
+        max_work=max_work,
+        timeout_ms=timeout_ms,
+    )
+    return ProofEngine.for_schemas(
+        s1, s2, dialect=resolved_dialect, options=options
+    ).join(s1, s2)
+
+
+def is_equivalent(
+    s1,
+    s2,
+    *,
+    dialect=None,
+    proof_options=None,
+    endeavor=False,
+    max_work=None,
+    timeout_ms=None,
+):
+    """Entry point for schema equivalence check operation."""
+    options = _resolve_proof_options(
+        proof_options,
+        endeavor=endeavor,
+        max_work=max_work,
+        timeout_ms=timeout_ms,
+    )
+    return is_subschema(
+        s1, s2, dialect=dialect, proof_options=options
+    ) and is_subschema(
+        s2,
+        s1,
+        dialect=dialect,
+        proof_options=options,
+    )