databricks-schema 0.5.0__tar.gz

databricks_schema-0.5.0/.github/workflows/ci.yml

@@ -0,0 +1,29 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint-and-test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Install dependencies
+        run: uv sync --all-groups
+
+      - name: Format check
+        run: uv run ruff format --check databricks_schema/ tests/
+
+      - name: Lint
+        run: uv run ruff check databricks_schema/ tests/
+
+      - name: Tests
+        run: uv run pytest

databricks_schema-0.5.0/.github/workflows/release.yml

@@ -0,0 +1,50 @@
+name: Release
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      contents: write  # required to upload assets to the release
+      id-token: write  # required for OIDC trusted publishing to PyPI
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Verify version matches tag
+        run: |
+          TAG="${{ github.ref_name }}"
+          TAG_VERSION="${TAG#v}"
+          TOML_VERSION=$(grep '^version = ' pyproject.toml | sed 's/version = "\(.*\)"/\1/')
+          echo "Tag version:    $TAG_VERSION"
+          echo "pyproject.toml: $TOML_VERSION"
+          if [ "$TAG_VERSION" != "$TOML_VERSION" ]; then
+            echo "ERROR: version mismatch — update pyproject.toml before tagging"
+            exit 1
+          fi
+
+      - name: Install dependencies
+        run: uv sync --all-groups
+
+      - name: Lint and test
+        run: |
+          uv run ruff check databricks_schema/ tests/
+          uv run pytest
+
+      - name: Build wheel and sdist
+        run: uv build
+
+      - name: Upload artifacts to release
+        run: gh release upload "${{ github.ref_name }}" dist/* --clobber
+        env:
+          GH_TOKEN: ${{ github.token }}
+
+      - name: Publish to PyPI
+        run: uv publish --trusted-publishing always

databricks_schema-0.5.0/.gitignore

@@ -0,0 +1,13 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+
+# Tests
+.test_output/

databricks_schema-0.5.0/.python-version

@@ -0,0 +1 @@
+3.13

databricks_schema-0.5.0/CLAUDE.md

@@ -0,0 +1,61 @@
+# CLAUDE.md
+
+## Project
+
+`databricks-schema` — CLI + Python library that extracts, diffs, and generates SQL for Databricks Unity Catalog schemas stored as YAML or JSON files (one file per schema). Pydantic v2 models serve as the intermediate representation for future bidirectional sync.
+
+## Key commands
+
+```bash
+uv sync --all-groups          # install deps (including dev)
+uv run pytest                 # run tests
+uv run ruff check databricks_schema/ tests/
+uv run ruff format databricks_schema/ tests/
+uv run databricks-schema --help
+```
+
+## Package layout
+
+```
+databricks_schema/
+  models.py      # Pydantic v2 models: Catalog, Schema, Table, Column, PrimaryKey, ForeignKey
+  extractor.py   # CatalogExtractor — wraps databricks-sdk
+  yaml_io.py     # schema/catalog to/from YAML and JSON; _strip_empty removes None + empty collections
+  diff.py        # diff_schemas / diff_catalog_with_dir; FieldChange, ColumnDiff, TableDiff, SchemaDiff, CatalogDiff
+  sql_gen.py     # schema_diff_to_sql — pure SQL generation from SchemaDiff; no SDK/IO
+  cli.py         # argparse CLI: extract, diff, generate-sql, list-catalogs, list-schemas
+  __init__.py    # public re-exports
+tests/
+  test_models.py
+  test_extractor.py  # all SDK calls mocked with MagicMock
+  test_yaml_io.py
+  test_diff.py       # pure model comparison, no SDK calls
+  test_sql_gen.py    # pure SQL generation tests, no SDK calls
+```
+
+## Conventions
+
+- Package manager: `uv`; do not use `pip` directly
+- Ruff: select E, W, F, I, UP; line-length 100; target py311
+- Use `X | None` not `Optional[X]`; use `datetime.UTC` not `timezone.utc`
+- `from __future__ import annotations` in every module
+- Imports at the top of each module — never inside functions
+- Use full package imports (`from databricks_schema.models import ...`), not relative imports (`from .models import ...`)
+- Tags = Unity Catalog governance key/value tags — not `properties`
+- FK refs store only `ref_schema` + `ref_table` (no catalog)
+- Column order in YAML = SDK position (None → 9999)
+- `_strip_empty`: removes `None` and empty `dict`/`list`; preserves `False`, `0`, empty strings
+- `yaml_io.py` has parallel YAML and JSON functions (`schema_to_yaml`/`schema_to_json`, etc.)
+- `diff_catalog_with_dir` accepts `fmt: Literal["yaml", "json"] = "yaml"` to select file format
+- CLI: catalog is a required positional argument (not a flag)
+- `extract` `--format`/`-f` selects output format (`yaml` default, `json` opt-in); dest is `fmt`
+- `diff` auto-detects format from files present in the directory; exits 2 on mixed YAML+JSON
+- `TableType` is re-exported from `databricks.sdk.service.catalog` — do not redefine it
+- `--include-metadata` flag (on `extract`, `diff`, `generate-sql`) enables `owner` + `storage_location`; both are excluded by default
+- `diff` command exits 0 (no changes) or 1 (differences found) — useful in CI
+- Diff result types are dataclasses (not Pydantic); comparison functions are pure (no SDK calls)
+- `generate-sql` auto-detects format from files; exits 2 on mixed YAML+JSON or empty directory
+- `generate-sql` destructive statements commented out by default; `--allow-drop` emits real DROPs
+- `sql_gen.py` is pure (no SDK, no I/O); diff direction: `FieldChange.old` = stored (target), `.new` = live
+- FK refs in SQL use same catalog as the source table (`ref_schema` + `ref_table` from model)
+- Unsupported field changes (`table_type`) emit `-- TODO: unsupported change: …` comments

databricks_schema-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 [yyyy] [name of copyright owner]
+
+   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.

databricks_schema-0.5.0/PKG-INFO

@@ -0,0 +1,293 @@
+Metadata-Version: 2.4
+Name: databricks-schema
+Version: 0.5.0
+Summary: Databricks Unity Catalog schema extractor
+License-File: LICENSE
+Requires-Python: >=3.11
+Requires-Dist: databricks-sdk>=0.64.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml>=6.0
+Description-Content-Type: text/markdown
+
+# databricks-schema
+
+A CLI tool and Python library that uses the Databricks SDK to extract and diff Unity Catalog schemas as YAML files. It can also generate Databricks Spark SQL to apply schema changes across catalogs.
+
+## Overview
+
+Extract a catalog to YAML files, then diff those files against a catalog — the same one to detect drift or a different one to compare environments (e.g. prod vs test):
+
+```bash
+# 1. Find the catalog you want to snapshot
+databricks-schema list-catalogs
+
+# 2. Extract its schemas to YAML files (one file per schema)
+databricks-schema extract prod_catalog --output-dir ./schemas/
+
+# 3. Diff those files against a catalog (same or different)
+databricks-schema diff test_catalog ./schemas/
+
+# 4. Generate SQL to bring that catalog in line with the YAML files
+databricks-schema generate-sql test_catalog ./schemas/ --output-dir ./migrations/
+```
+
+The YAML files act as a version-controllable snapshot of your schema. The `diff` command exits with code `1` when differences are found, making it suitable for CI pipelines.
+
+## Output Format
+
+Each schema is written to `{output-dir}/{schema-name}.yaml`. Fields with no value (null comments, empty tag dicts, empty FK lists) are omitted. Use `--format json` to write `.json` files with the same structure.
+
+```yaml
+name: main
+comment: Main production schema
+tags:
+  env: prod
+tables:
+  - name: users
+    table_type: MANAGED
+    comment: User accounts
+    tags:
+      domain: identity
+    columns:
+      - name: id
+        data_type: bigint
+        nullable: false
+        comment: Primary key
+      - name: email
+        data_type: string
+      - name: org_id
+        data_type: bigint
+    primary_key:
+      name: pk_users
+      columns:
+        - id
+    foreign_keys:
+      - name: fk_org
+        columns:
+          - org_id
+        ref_schema: orgs
+        ref_table: organizations
+        ref_columns:
+          - id
+```
+
+## Installation
+
+Requires Python 3.11+ and [uv](https://github.com/astral-sh/uv).
+
+```bash
+git clone <repo>
+cd databricks-schema
+uv sync
+```
+
+For development (includes pytest and ruff):
+
+```bash
+uv sync --all-groups
+```
+
+## Authentication
+
+The tool uses the [Databricks SDK](https://github.com/databricks/databricks-sdk-py) for auth. Configure it via environment variables:
+
+```bash
+export DATABRICKS_HOST=https://<workspace>.cloud.databricks.com
+export DATABRICKS_TOKEN=<your-personal-access-token>
+```
+
+Or use a [Databricks CLI profile](https://docs.databricks.com/dev-tools/cli/profiles.html) (`~/.databrickscfg`) — the SDK will pick it up automatically.
+
+You can also pass credentials directly as flags (see `--host` / `--token` below).
+
+## CLI Usage
+
+```
+databricks-schema [OPTIONS] COMMAND [ARGS]...
+```
+
+### `extract`
+
+Extract all schemas from a catalog to YAML files:
+
+```bash
+databricks-schema extract <catalog> --output-dir ./schemas/
+```
+
+Use `--format json` to write `.json` files instead of `.yaml`.
+
+Extract specific schemas only:
+
+```bash
+databricks-schema extract <catalog> --schema main --schema raw --output-dir ./schemas/
+```
+
+Print a single schema to stdout (no `--output-dir`):
+
+```bash
+databricks-schema extract <catalog> --schema main
+```
+
+Skip tag lookups for faster extraction (tags will be absent from output):
+
+```bash
+databricks-schema extract <catalog> --output-dir ./schemas/ --no-tags
+```
+
+Include additional metadata (`owner`, `storage_location`) in the output:
+
+```bash
+databricks-schema extract <catalog> --output-dir ./schemas/ --include-metadata
+```
+
+Control the number of parallel workers (default: 4):
+
+```bash
+databricks-schema extract <catalog> --output-dir ./schemas/ --workers 8
+```
+
+### `diff`
+
+Compare the live catalog against previously extracted schema files (format auto-detected from the directory — YAML or JSON, not mixed):
+
+```bash
+databricks-schema diff <catalog> ./schemas/
+```
+
+Compare specific schemas only:
+
+```bash
+databricks-schema diff <catalog> ./schemas/ --schema main --schema raw
+```
+
+Skip tag lookups during comparison:
+
+```bash
+databricks-schema diff <catalog> ./schemas/ --no-tags
+```
+
+Include additional metadata (`owner`, `storage_location`) in the comparison:
+
+```bash
+databricks-schema diff <catalog> ./schemas/ --include-metadata
+```
+
+Exits with code `0` if no differences are found, `1` if there are — making it suitable for CI pipelines. Output example:
+
+```
+~ Schema: main [MODIFIED]
+  ~ Table: users [MODIFIED]
+    ~ Column: score [MODIFIED]
+        data_type: 'int' -> 'double'
+    + Column: phone [ADDED]
+  + Table: events [ADDED]
+- Schema: legacy [REMOVED]
+```
+
+Markers: `+` added in catalog, `-` removed from catalog, `~` modified.
+
+### `generate-sql`
+
+Generate Databricks Spark SQL statements to bring the live catalog in line with local schema files (format auto-detected, YAML or JSON, not mixed). Statements are printed to stdout by default:
+
+```bash
+databricks-schema generate-sql <catalog> ./schemas/
+```
+
+Write one `.sql` file per schema to a directory instead:
+
+```bash
+databricks-schema generate-sql <catalog> ./schemas/ --output-dir ./migrations/
+```
+
+Destructive statements (`DROP SCHEMA`, `DROP TABLE`, `DROP COLUMN`) are emitted as SQL comments by default. Pass `--allow-drop` to emit them as executable statements:
+
+```bash
+databricks-schema generate-sql <catalog> ./schemas/ --allow-drop
+```
+
+Filter to specific schemas:
+
+```bash
+databricks-schema generate-sql <catalog> ./schemas/ --schema main --schema raw
+```
+
+Skip tag lookups for faster comparison:
+
+```bash
+databricks-schema generate-sql <catalog> ./schemas/ --no-tags
+```
+
+Include additional metadata (`owner`, `storage_location`) in the comparison:
+
+```bash
+databricks-schema generate-sql <catalog> ./schemas/ --include-metadata
+```
+
+### `list-catalogs`
+
+List all accessible catalogs:
+
+```bash
+databricks-schema list-catalogs
+```
+
+### `list-schemas`
+
+List schemas in a catalog:
+
+```bash
+databricks-schema list-schemas <catalog>
+```
+
+## Python Library Usage
+
+```python
+from pathlib import Path
+from databricks_schema import CatalogExtractor, catalog_to_yaml, schema_from_yaml
+from databricks_schema import diff_catalog_with_dir, diff_schemas, schema_diff_to_sql
+
+# Extract using configured auth (max_workers controls parallel table extraction)
+extractor = CatalogExtractor(max_workers=4)
+catalog = extractor.extract_catalog("my_catalog", schema_filter=["main", "raw"])
+
+# Skip tag lookups for faster extraction
+catalog = extractor.extract_catalog("my_catalog", include_tags=False)
+
+# Include additional metadata (owner, storage_location)
+catalog = extractor.extract_catalog("my_catalog", include_metadata=True)
+
+# Serialise to YAML
+yaml_text = catalog_to_yaml(catalog)
+
+# Deserialise from YAML
+schema = schema_from_yaml(open("schemas/main.yaml").read())
+print(schema.tables[0].columns)
+
+# Compare live catalog against local YAML files
+result = diff_catalog_with_dir(catalog, Path("./schemas/"))
+if result.has_changes:
+    for schema_diff in result.schemas:
+        print(schema_diff.name, schema_diff.status)
+
+# Compare two Schema objects directly
+stored = schema_from_yaml(open("schemas/main.yaml").read())
+diff = diff_schemas(live=catalog.schemas[0], stored=stored)
+
+# Generate SQL to bring live in line with stored
+sql = schema_diff_to_sql("my_catalog", diff, stored_schema=stored, allow_drop=False)
+print(sql)
+```
+
+## Development
+
+```bash
+# Run tests
+uv run pytest
+
+# Lint
+uv run ruff check databricks_schema/ tests/
+
+# Format
+uv run ruff format databricks_schema/ tests/
+```