relational-schema-analyzer 0.1.0__tar.gz

relational_schema_analyzer-0.1.0/.github/workflows/ci.yml

@@ -0,0 +1,39 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  lint-and-test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install (dev + extras under test)
+        run: |
+          python -m pip install --upgrade pip
+          # postgres: psycopg is imported eagerly by the PG connector module.
+          # csv: polars backs the CSV connector. owl: rdflib for OWL round-trip tests.
+          # dev pulls fakesnow + snowflake-connector-python for the always-on
+          # Snowflake conformance tests (embedded emulator, no cloud).
+          # mysql/mssql drivers are intentionally NOT installed so their
+          # "missing driver" paths are tested. Live-DB tests are opt-in (see
+          # integration.yml) and skip here because RUN_INTEGRATION is unset.
+          python -m pip install -e ".[dev,postgres,csv,owl,duckdb,mcp]"
+
+      - name: Ruff
+        run: ruff check .
+
+      - name: Pytest
+        run: pytest -q

relational_schema_analyzer-0.1.0/.github/workflows/integration.yml

@@ -0,0 +1,66 @@
+name: Integration (live databases)
+
+# Live-DB conformance against Docker service containers. Runs the opt-in
+# `integration` tests (RUN_INTEGRATION=1) against real Postgres + MySQL. SQL
+# Server and cloud warehouses (Snowflake/Databricks) plug in via DSN env/secrets
+# using the same harness; Snowflake also has always-on embedded coverage via
+# fakesnow in the main CI workflow.
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+jobs:
+  live:
+    runs-on: ubuntu-latest
+    # Ephemeral throwaway databases: trust / empty-password auth so no credentials
+    # are committed (nothing for secret scanners to flag). Not a security model for
+    # anything beyond a disposable CI container on localhost.
+    services:
+      postgres:
+        image: postgres:16
+        env:
+          POSTGRES_USER: postgres
+          POSTGRES_HOST_AUTH_METHOD: trust
+          POSTGRES_DB: rsa_it
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd "pg_isready -U postgres"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+      mysql:
+        image: mysql:8
+        env:
+          MYSQL_ALLOW_EMPTY_PASSWORD: "yes"
+          MYSQL_DATABASE: rsa_it
+        ports:
+          - 3306:3306
+        options: >-
+          --health-cmd "mysqladmin ping -h 127.0.0.1 --silent"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 10
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install (drivers under test)
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev,postgres,mysql,csv,owl]"
+
+      - name: Run integration conformance
+        env:
+          RUN_INTEGRATION: "1"
+          # No credentials in the DSNs (trust / empty-password containers above).
+          RSA_PG_DSN: postgresql://postgres@localhost:5432/rsa_it
+          RSA_MYSQL_DSN: mysql://root@localhost:3306/rsa_it
+        run: pytest -m integration -q

relational_schema_analyzer-0.1.0/.gitignore

@@ -0,0 +1,21 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.eggs/
+build/
+dist/
+.venv/
+venv/
+.env
+
+# Tooling
+.coverage
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+
+# OS / editor
+.DS_Store
+.idea/
+.vscode/

relational_schema_analyzer-0.1.0/LICENSE

@@ -0,0 +1,174 @@
+                                 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.
+
+   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
+

relational_schema_analyzer-0.1.0/PKG-INFO

@@ -0,0 +1,139 @@
+Metadata-Version: 2.4
+Name: relational-schema-analyzer
+Version: 0.1.0
+Summary: Analyze a relational database schema into a conceptual model (OWL-capable) with mapping back to the source schema.
+Project-URL: Homepage, https://github.com/ArthurKeen/relational-schema-analyzer
+Project-URL: Repository, https://github.com/ArthurKeen/relational-schema-analyzer
+Project-URL: Issues, https://github.com/ArthurKeen/relational-schema-analyzer/issues
+Author: Arthur Keen
+License: Apache-2.0
+License-File: LICENSE
+Keywords: conceptual-model,mysql,ontology,owl,postgres,relational,schema,snowflake
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Database
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: jsonschema>=4
+Requires-Dist: pydantic>=2
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.30; extra == 'anthropic'
+Provides-Extra: csv
+Requires-Dist: polars>=0.20; extra == 'csv'
+Provides-Extra: databricks
+Requires-Dist: databricks-sql-connector>=3; extra == 'databricks'
+Provides-Extra: dev
+Requires-Dist: duckdb>=1; extra == 'dev'
+Requires-Dist: fakesnow>=0.11; extra == 'dev'
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Requires-Dist: snowflake-connector-python>=3; extra == 'dev'
+Provides-Extra: duckdb
+Requires-Dist: duckdb>=1; extra == 'duckdb'
+Provides-Extra: mcp
+Requires-Dist: mcp>=1; extra == 'mcp'
+Provides-Extra: mysql
+Requires-Dist: pymysql>=1; extra == 'mysql'
+Provides-Extra: openai
+Requires-Dist: openai>=1; extra == 'openai'
+Provides-Extra: openrouter
+Requires-Dist: httpx>=0.27; extra == 'openrouter'
+Provides-Extra: owl
+Requires-Dist: rdflib>=7; extra == 'owl'
+Provides-Extra: postgres
+Requires-Dist: psycopg[binary]>=3; extra == 'postgres'
+Provides-Extra: snowflake
+Requires-Dist: snowflake-connector-python>=3; extra == 'snowflake'
+Provides-Extra: sqlserver
+Requires-Dist: pymssql>=2; extra == 'sqlserver'
+Description-Content-Type: text/markdown
+
+# relational-schema-analyzer
+
+Analyze a **relational database schema** and produce a canonical **conceptual model**
+(entities / relationships / properties), a **conceptual → physical mapping** back to the
+source relational schema, and **metadata** (confidence, fingerprints, patterns). Optional
+exports include **OWL** (Turtle / JSON-LD) for ontology pipelines.
+
+This library is the relational analogue of
+[`arangodb-schema-analyzer`](https://pypi.org/project/arangodb-schema-analyzer/) and
+emits the **same tool-contract bundle shape** so that downstream consumers
+(`arango-ontoextract`, transpilers, and ETL tools such as `r2g`) can treat relational and
+ArangoDB sources interchangeably.
+
+```text
+PostgreSQL / MySQL / SQL Server / Snowflake / CSV
+        │
+        ▼  introspect (live catalog views, not DDL parsing)
+   Physical Schema  (tables, columns, PKs, FKs, types)
+        │
+        ▼  infer (deterministic baseline + optional LLM refinement)
+   { conceptualSchema, physicalMapping, metadata }   ← canonical JSON bundle
+        │
+        ├──► OWL Turtle / JSON-LD       (arango-ontoextract, ontology tooling)
+        ├──► relational physical view   (SQL-native query tooling, future)
+        └──► consumed by r2g            (drives ArangoDB MappingConfig generation)
+```
+
+## Status
+
+Early development. **Phases 0–3 implemented**: the physical core (connectors, types,
+FK inference) is extracted from `r2g`; the deterministic conceptual baseline emits a
+contract-valid `{conceptualSchema, physicalMapping, metadata}` bundle with no LLM; and
+OWL (Turtle / JSON-LD) exports + a CLI are in place. Next: optional LLM refinement
+(Phase 4) and ecosystem integration (Phase 5). See:
+
+- [`docs/DESIGN.md`](docs/DESIGN.md) — architecture, data model, tool contract, OWL mapping
+- [`docs/IMPLEMENTATION-PLAN.md`](docs/IMPLEMENTATION-PLAN.md) — phased delivery plan & extraction inventory
+
+```python
+from relational_schema_analyzer import (
+    create_connector, RelationalSchemaAnalyzer, export_owl_turtle,
+)
+
+physical = create_connector("postgresql", url, schema_name="public").get_schema()
+analysis = RelationalSchemaAnalyzer().analyze(physical)   # baseline, no LLM
+bundle = analysis.to_bundle()    # {conceptualSchema, physicalMapping, metadata}
+ttl = export_owl_turtle(analysis)
+
+# Optional LLM refinement (additive; falls back to baseline on any error):
+refined = RelationalSchemaAnalyzer(
+    llm_provider="openai",           # or "anthropic" / "openrouter" / a provider object
+).analyze(physical)                  # better names + embed/n-ary hints
+```
+
+```bash
+relational-schema-analyzer snapshot --source postgresql --url "$DSN" -o physical.json
+relational-schema-analyzer analyze  --from-snapshot physical.json --pretty
+relational-schema-analyzer owl      --from-snapshot physical.json --format turtle -o schema.ttl
+```
+
+Sources: `postgresql`, `mysql`, `sqlserver`, `snowflake`, `duckdb`, `databricks`, `csv`.
+
+**MCP server** (optional, `pip install 'relational-schema-analyzer[mcp]'`) exposes the same
+`snapshot` / `analyze` / `owl` operations over the v1 tool contract:
+
+```bash
+relational-schema-analyzer-mcp                                   # stdio (local IDE)
+relational-schema-analyzer-mcp --transport sse --host 0.0.0.0 --port 8000   # remote (set RSA_MCP_TOKEN)
+```
+
+## Why this exists
+
+Most of the relational **introspection** layer already exists and is battle-tested inside
+the `r2g` (relational-to-graph) project, but it is welded to ArangoDB ETL and cannot be
+reused elsewhere. This repo extracts that core into a paradigm-neutral library and adds the
+**conceptual / OWL layer** that `r2g` never had, conforming to the contract the ArangoDB
+analyzer already publishes.
+
+## License
+
+Apache-2.0 — matching the surrounding Arango ecosystem libraries
+(`arangodb-schema-analyzer`, `r2g`). See [`LICENSE`](LICENSE).

relational_schema_analyzer-0.1.0/README.md

@@ -0,0 +1,82 @@
+# relational-schema-analyzer
+
+Analyze a **relational database schema** and produce a canonical **conceptual model**
+(entities / relationships / properties), a **conceptual → physical mapping** back to the
+source relational schema, and **metadata** (confidence, fingerprints, patterns). Optional
+exports include **OWL** (Turtle / JSON-LD) for ontology pipelines.
+
+This library is the relational analogue of
+[`arangodb-schema-analyzer`](https://pypi.org/project/arangodb-schema-analyzer/) and
+emits the **same tool-contract bundle shape** so that downstream consumers
+(`arango-ontoextract`, transpilers, and ETL tools such as `r2g`) can treat relational and
+ArangoDB sources interchangeably.
+
+```text
+PostgreSQL / MySQL / SQL Server / Snowflake / CSV
+        │
+        ▼  introspect (live catalog views, not DDL parsing)
+   Physical Schema  (tables, columns, PKs, FKs, types)
+        │
+        ▼  infer (deterministic baseline + optional LLM refinement)
+   { conceptualSchema, physicalMapping, metadata }   ← canonical JSON bundle
+        │
+        ├──► OWL Turtle / JSON-LD       (arango-ontoextract, ontology tooling)
+        ├──► relational physical view   (SQL-native query tooling, future)
+        └──► consumed by r2g            (drives ArangoDB MappingConfig generation)
+```
+
+## Status
+
+Early development. **Phases 0–3 implemented**: the physical core (connectors, types,
+FK inference) is extracted from `r2g`; the deterministic conceptual baseline emits a
+contract-valid `{conceptualSchema, physicalMapping, metadata}` bundle with no LLM; and
+OWL (Turtle / JSON-LD) exports + a CLI are in place. Next: optional LLM refinement
+(Phase 4) and ecosystem integration (Phase 5). See:
+
+- [`docs/DESIGN.md`](docs/DESIGN.md) — architecture, data model, tool contract, OWL mapping
+- [`docs/IMPLEMENTATION-PLAN.md`](docs/IMPLEMENTATION-PLAN.md) — phased delivery plan & extraction inventory
+
+```python
+from relational_schema_analyzer import (
+    create_connector, RelationalSchemaAnalyzer, export_owl_turtle,
+)
+
+physical = create_connector("postgresql", url, schema_name="public").get_schema()
+analysis = RelationalSchemaAnalyzer().analyze(physical)   # baseline, no LLM
+bundle = analysis.to_bundle()    # {conceptualSchema, physicalMapping, metadata}
+ttl = export_owl_turtle(analysis)
+
+# Optional LLM refinement (additive; falls back to baseline on any error):
+refined = RelationalSchemaAnalyzer(
+    llm_provider="openai",           # or "anthropic" / "openrouter" / a provider object
+).analyze(physical)                  # better names + embed/n-ary hints
+```
+
+```bash
+relational-schema-analyzer snapshot --source postgresql --url "$DSN" -o physical.json
+relational-schema-analyzer analyze  --from-snapshot physical.json --pretty
+relational-schema-analyzer owl      --from-snapshot physical.json --format turtle -o schema.ttl
+```
+
+Sources: `postgresql`, `mysql`, `sqlserver`, `snowflake`, `duckdb`, `databricks`, `csv`.
+
+**MCP server** (optional, `pip install 'relational-schema-analyzer[mcp]'`) exposes the same
+`snapshot` / `analyze` / `owl` operations over the v1 tool contract:
+
+```bash
+relational-schema-analyzer-mcp                                   # stdio (local IDE)
+relational-schema-analyzer-mcp --transport sse --host 0.0.0.0 --port 8000   # remote (set RSA_MCP_TOKEN)
+```
+
+## Why this exists
+
+Most of the relational **introspection** layer already exists and is battle-tested inside
+the `r2g` (relational-to-graph) project, but it is welded to ArangoDB ETL and cannot be
+reused elsewhere. This repo extracts that core into a paradigm-neutral library and adds the
+**conceptual / OWL layer** that `r2g` never had, conforming to the contract the ArangoDB
+analyzer already publishes.
+
+## License
+
+Apache-2.0 — matching the surrounding Arango ecosystem libraries
+(`arangodb-schema-analyzer`, `r2g`). See [`LICENSE`](LICENSE).