pipeloom-databricks 0.5.0__tar.gz

pipeloom_databricks-0.5.0/.gitignore

@@ -0,0 +1,16 @@
+__pycache__/
+*.py[cod]
+.venv/
+build/
+dist/
+*.egg-info/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+coverage.xml
+htmlcov/
+site/
+target/
+.pipeloom/
+.env

pipeloom_databricks-0.5.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

pipeloom_databricks-0.5.0/NOTICE

@@ -0,0 +1,2 @@
+pipeloom
+Copyright 2026 Emanuel Luis

pipeloom_databricks-0.5.0/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.5
+Name: pipeloom-databricks
+Version: 0.5.0
+Summary: Databricks renderer for pipeloom: a compiled plan as Jobs settings JSON and bundle YAML.
+Project-URL: Repository, https://github.com/emanuel-luis/pipeloom
+Project-URL: Documentation, https://emanuel-luis.github.io/pipeloom/
+Project-URL: Changelog, https://github.com/emanuel-luis/pipeloom/blob/main/CHANGELOG.md
+Author-email: Emanuel Luis <emanuel.filho08@gmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Keywords: bundles,data-engineering,databricks,jobs,pipelines,pipeloom
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Requires-Dist: databricks-sdk<1,>=0.50
+Requires-Dist: pipeloom-spark~=0.5.0
+Requires-Dist: pipeloom~=0.5.0
+Description-Content-Type: text/markdown
+
+# pipeloom-databricks
+
+The Databricks renderer for [pipeloom](https://github.com/emanuel-luis/pipeloom). It turns a
+compiled plan into Databricks Jobs settings (JSON for the Jobs API) and into a bundle YAML file.
+
+```console
+$ pip install "pipeloom[databricks]"
+```
+
+Describe the deployment in a target:
+
+```yaml
+targets:
+  prod:
+    engine: {kind: spark}
+    catalog: {kind: spark_catalog}
+    state: {kind: table, table: ops._pipeloom_state}   # shared by every task
+    artifacts: {root: /Volumes/main/ops/pipeloom}
+    deploy:
+      kind: databricks
+      pipelines: {main: {}, daily: {select: ["tag:daily"]}}
+      compute:
+        default: {kind: serverless, environment_version: "5"}
+      task_grouping: none        # none, by_tag or by_folder
+```
+
+- One job per pipeline, one task per unit (or per group of units), plus a finalize task that
+  closes the run. A job above 1,000 tasks is an error (PLD001).
+- Rendering is pure: no network, no Databricks SDK call and no credentials are needed. The
+  output is byte-for-byte the same for the same plan.
+- Compute is serverless environments or job clusters, chosen per model with `compute_rules`.
+- A pipeline job runs only its own units. An upstream model in another pipeline is read from
+  its persisted output, so schedule that pipeline first.
+- Diagnostics: PLD001 (task limit), PLD003 (group cycle), PLD004 (invalid deploy options),
+  PLD005 (compute rule that matches no model), PLD013 (unresolved task parameter).
+- Bundles: `pipeloom databricks bundle --target prod --out resources` writes one job file and
+  one manifest per pipeline into a Declarative Automation Bundle (the output folder must lie
+  inside the bundle, next to `databricks.yml`; add the job files to its `include`). Paths use
+  `${workspace.file_path}`. `--check` lists stale files and exits 1.
+- Tasks run `pipeloom_databricks_task`, a wrapper that calls pipeloom in the task's own process,
+  so an existing Spark session is reused. A parameter that Databricks left as `{{...}}` stops
+  the task with PLD013. After a unit task the wrapper sets the task value `pipeloom`, a small
+  summary of its units (best effort).
+- `pipeloom_databricks.testing.jobsim.simulate_job` runs a rendered job locally for tests.
+- Direct deploy: `pipeloom databricks [--profile NAME] deploy --target prod [--pipeline NAME]...
+  [--dry-run]` uploads the project to the workspace (content addressed, under
+  `<workspace_root>/<project>/<pipeline>/<target>/<hash>`) and creates or resets one job per
+  pipeline, found by its `pipeloom_job` tag. It prints one JSON line per pipeline. `--dry-run`
+  prints the job settings and connects to nothing. The upload holds `pipeloom.yml`, the model
+  files and the `*.py` files below `python_paths` (virtual environments, `dist`, `build` and
+  similar folders are skipped). Other files below `python_paths` are not uploaded, so a Python
+  model that reads a file next to it (`.sql`, `.json`, `.csv`) works locally but not on
+  Databricks; keep such data in a table or a volume. Notebooks and files above 10 MB are refused
+  (PLD012).
+- Connection: `--profile`, else a `DATABRICKS_CONFIG_PROFILE` you set, else `DATABRICKS_HOST`
+  with credentials, else the Databricks runtime, else PLD010. pipeloom never picks a profile
+  by itself. Other codes: PLD006 (two jobs with the same tag), PLD009 (API error).
+- `pipeloom_databricks.api` is the stable surface for other distributions, and
+  `pipeloom_databricks.testing.fake.FakeDatabricks` a fake workspace for tests.
+- Run: `pipeloom databricks run --target prod [--pipeline NAME] [--select S]... [--exclude S]...
+  [--run-id RID] [--full-refresh] [--ensure] [--ephemeral] [--wait|--no-wait]` starts the
+  deployed job (PLD007 when none is deployed, PLD008 when it differs from the local render,
+  unless `--ensure` deploys first). Selected units map to task keys plus finalize (`only`); a
+  partly selected group runs whole, with the warning PLD015. `--timeout SECONDS` (default 24
+  hours) bounds `--wait`. `--run-id` names the run and makes the start
+  idempotent. `--ephemeral` uploads the project and submits a one-time run on serverless
+  compute. It prints one JSON line with the ids and the run page URL, then with `--wait` (the
+  default) polls every 15 seconds, reports task transitions and the failed units, and exits 1
+  unless the run succeeded.
+- Repair: `pipeloom databricks repair --target prod (--run-id RID | --job-run-id N)
+  [--wait|--no-wait]` reruns the tasks that failed, timed out, were cancelled or skipped, plus
+  finalize. A run that is still active is PLD014; nothing to repair exits 0.
+- Finalize reads how each task ended from the Jobs API and gives core finalize the state of every
+  unit that wrote no attempt file, so a lost, timed-out or cancelled task fails or cancels the
+  run (a failed one is PLD011). If the API cannot be read, finalize prints one warning and judges
+  by the attempt files alone. A one-time run has no job run id, so it gets no task states.
+
+- Unity Catalog: `catalog: {kind: unity, catalog: main}` (Spark engine only) addresses tables and
+  views as `` `catalog`.`schema`.`name` ``. The option catalog fills in when the target's naming
+  leaves it empty. A schema is created only when it does not exist yet, so a principal without
+  CREATE SCHEMA can write to an existing one.
+- Secrets: `${secret:databricks/<scope>/<key>}` in plugin options reads a Databricks secret
+  scope at run time, with the connection rules above. The value is masked like any resolved
+  secret. A bad path, a missing connection or an API error is PLX109, naming the path and never
+  the value.
+
+License: Apache-2.0.

pipeloom_databricks-0.5.0/README.md

@@ -0,0 +1,87 @@
+# pipeloom-databricks
+
+The Databricks renderer for [pipeloom](https://github.com/emanuel-luis/pipeloom). It turns a
+compiled plan into Databricks Jobs settings (JSON for the Jobs API) and into a bundle YAML file.
+
+```console
+$ pip install "pipeloom[databricks]"
+```
+
+Describe the deployment in a target:
+
+```yaml
+targets:
+  prod:
+    engine: {kind: spark}
+    catalog: {kind: spark_catalog}
+    state: {kind: table, table: ops._pipeloom_state}   # shared by every task
+    artifacts: {root: /Volumes/main/ops/pipeloom}
+    deploy:
+      kind: databricks
+      pipelines: {main: {}, daily: {select: ["tag:daily"]}}
+      compute:
+        default: {kind: serverless, environment_version: "5"}
+      task_grouping: none        # none, by_tag or by_folder
+```
+
+- One job per pipeline, one task per unit (or per group of units), plus a finalize task that
+  closes the run. A job above 1,000 tasks is an error (PLD001).
+- Rendering is pure: no network, no Databricks SDK call and no credentials are needed. The
+  output is byte-for-byte the same for the same plan.
+- Compute is serverless environments or job clusters, chosen per model with `compute_rules`.
+- A pipeline job runs only its own units. An upstream model in another pipeline is read from
+  its persisted output, so schedule that pipeline first.
+- Diagnostics: PLD001 (task limit), PLD003 (group cycle), PLD004 (invalid deploy options),
+  PLD005 (compute rule that matches no model), PLD013 (unresolved task parameter).
+- Bundles: `pipeloom databricks bundle --target prod --out resources` writes one job file and
+  one manifest per pipeline into a Declarative Automation Bundle (the output folder must lie
+  inside the bundle, next to `databricks.yml`; add the job files to its `include`). Paths use
+  `${workspace.file_path}`. `--check` lists stale files and exits 1.
+- Tasks run `pipeloom_databricks_task`, a wrapper that calls pipeloom in the task's own process,
+  so an existing Spark session is reused. A parameter that Databricks left as `{{...}}` stops
+  the task with PLD013. After a unit task the wrapper sets the task value `pipeloom`, a small
+  summary of its units (best effort).
+- `pipeloom_databricks.testing.jobsim.simulate_job` runs a rendered job locally for tests.
+- Direct deploy: `pipeloom databricks [--profile NAME] deploy --target prod [--pipeline NAME]...
+  [--dry-run]` uploads the project to the workspace (content addressed, under
+  `<workspace_root>/<project>/<pipeline>/<target>/<hash>`) and creates or resets one job per
+  pipeline, found by its `pipeloom_job` tag. It prints one JSON line per pipeline. `--dry-run`
+  prints the job settings and connects to nothing. The upload holds `pipeloom.yml`, the model
+  files and the `*.py` files below `python_paths` (virtual environments, `dist`, `build` and
+  similar folders are skipped). Other files below `python_paths` are not uploaded, so a Python
+  model that reads a file next to it (`.sql`, `.json`, `.csv`) works locally but not on
+  Databricks; keep such data in a table or a volume. Notebooks and files above 10 MB are refused
+  (PLD012).
+- Connection: `--profile`, else a `DATABRICKS_CONFIG_PROFILE` you set, else `DATABRICKS_HOST`
+  with credentials, else the Databricks runtime, else PLD010. pipeloom never picks a profile
+  by itself. Other codes: PLD006 (two jobs with the same tag), PLD009 (API error).
+- `pipeloom_databricks.api` is the stable surface for other distributions, and
+  `pipeloom_databricks.testing.fake.FakeDatabricks` a fake workspace for tests.
+- Run: `pipeloom databricks run --target prod [--pipeline NAME] [--select S]... [--exclude S]...
+  [--run-id RID] [--full-refresh] [--ensure] [--ephemeral] [--wait|--no-wait]` starts the
+  deployed job (PLD007 when none is deployed, PLD008 when it differs from the local render,
+  unless `--ensure` deploys first). Selected units map to task keys plus finalize (`only`); a
+  partly selected group runs whole, with the warning PLD015. `--timeout SECONDS` (default 24
+  hours) bounds `--wait`. `--run-id` names the run and makes the start
+  idempotent. `--ephemeral` uploads the project and submits a one-time run on serverless
+  compute. It prints one JSON line with the ids and the run page URL, then with `--wait` (the
+  default) polls every 15 seconds, reports task transitions and the failed units, and exits 1
+  unless the run succeeded.
+- Repair: `pipeloom databricks repair --target prod (--run-id RID | --job-run-id N)
+  [--wait|--no-wait]` reruns the tasks that failed, timed out, were cancelled or skipped, plus
+  finalize. A run that is still active is PLD014; nothing to repair exits 0.
+- Finalize reads how each task ended from the Jobs API and gives core finalize the state of every
+  unit that wrote no attempt file, so a lost, timed-out or cancelled task fails or cancels the
+  run (a failed one is PLD011). If the API cannot be read, finalize prints one warning and judges
+  by the attempt files alone. A one-time run has no job run id, so it gets no task states.
+
+- Unity Catalog: `catalog: {kind: unity, catalog: main}` (Spark engine only) addresses tables and
+  views as `` `catalog`.`schema`.`name` ``. The option catalog fills in when the target's naming
+  leaves it empty. A schema is created only when it does not exist yet, so a principal without
+  CREATE SCHEMA can write to an existing one.
+- Secrets: `${secret:databricks/<scope>/<key>}` in plugin options reads a Databricks secret
+  scope at run time, with the connection rules above. The value is masked like any resolved
+  secret. A bad path, a missing connection or an API error is PLX109, naming the path and never
+  the value.
+
+License: Apache-2.0.

pipeloom_databricks-0.5.0/pyproject.toml

@@ -0,0 +1,56 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "pipeloom-databricks"
+version = "0.5.0"
+description = "Databricks renderer for pipeloom: a compiled plan as Jobs settings JSON and bundle YAML."
+readme = "README.md"
+requires-python = ">=3.11"
+license = "Apache-2.0"
+license-files = ["LICENSE", "NOTICE"]
+authors = [{ name = "Emanuel Luis", email = "emanuel.filho08@gmail.com" }]
+keywords = ["pipeloom", "databricks", "jobs", "bundles", "data-engineering", "pipelines"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Typing :: Typed",
+]
+dependencies = ["pipeloom~=0.5.0", "pipeloom-spark~=0.5.0", "databricks-sdk>=0.50,<1"]
+
+[project.urls]
+Repository = "https://github.com/emanuel-luis/pipeloom"
+Documentation = "https://emanuel-luis.github.io/pipeloom/"
+Changelog = "https://github.com/emanuel-luis/pipeloom/blob/main/CHANGELOG.md"
+
+[project.entry-points."pipeloom.renderers"]
+databricks = "pipeloom_databricks.spec:RENDERER_SPEC"
+
+[project.entry-points."pipeloom.catalogs"]
+unity = "pipeloom_databricks.spec:UNITY_SPEC"
+
+[project.entry-points."pipeloom.secret_providers"]
+databricks = "pipeloom_databricks.spec:SECRETS_SPEC"
+
+[project.entry-points."pipeloom.commands"]
+databricks = "pipeloom_databricks.cli:databricks"
+
+[project.scripts]
+pipeloom_databricks_task = "pipeloom_databricks.task:main"
+
+[tool.uv.sources]
+pipeloom = { workspace = true }
+pipeloom-spark = { workspace = true }
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/pipeloom_databricks"]
+
+[tool.hatch.build.targets.sdist]
+only-include = ["src", "tests", "LICENSE", "NOTICE", "README.md"]

pipeloom_databricks-0.5.0/src/pipeloom_databricks/__init__.py

@@ -0,0 +1,18 @@
+"""Databricks renderer for pipeloom: a compiled plan as Jobs settings JSON and bundle YAML.
+
+Rendering is pure. Nothing here imports `databricks.sdk`; only the modules that talk to a
+workspace will, and they load it lazily.
+"""
+
+from __future__ import annotations
+
+
+def pipeloom_databricks_task() -> None:
+    """The entry point of a rendered task, found by `package_name` and `entry_point`.
+
+    A function of the package covers a Databricks lookup that does not read entry points. The
+    task module loads only when a task runs.
+    """
+    from pipeloom_databricks.task import main
+
+    main()

pipeloom_databricks-0.5.0/src/pipeloom_databricks/api.py

@@ -0,0 +1,45 @@
+"""The stable surface other pipeloom distributions (such as an Airflow renderer) may call.
+
+Importing it loads no SDK: `connect` imports `databricks.sdk` only when it runs.
+"""
+
+from __future__ import annotations
+
+from pipeloom_databricks.client import (
+    ApiError,
+    ConnectionNotConfigured,
+    DatabricksClient,
+    JobSummary,
+    RunInfo,
+    TaskRunInfo,
+    connect,
+)
+from pipeloom_databricks.deploy import DeployResult, DuplicateJobs, deploy, find_job
+from pipeloom_databricks.finalize_states import task_states
+from pipeloom_databricks.grouping import task_key_map
+from pipeloom_databricks.render import deploy_options, render_job
+from pipeloom_databricks.repair import repair
+from pipeloom_databricks.run import RunStarted, SelectionError, find_run, run_job
+
+__all__ = [
+    "ApiError",
+    "ConnectionNotConfigured",
+    "DatabricksClient",
+    "DeployResult",
+    "DuplicateJobs",
+    "JobSummary",
+    "RunInfo",
+    "RunStarted",
+    "SelectionError",
+    "TaskRunInfo",
+    "connect",
+    "deploy",
+    "deploy_options",
+    "find_job",
+    "find_run",
+    "render_job",
+    "repair",
+    "run_job",
+    "task_key_map",
+    "task_states",
+]

pipeloom_databricks-0.5.0/src/pipeloom_databricks/bundle.py

@@ -0,0 +1,113 @@
+"""The files of a Declarative Automation Bundle: one job file and one stable manifest per pipeline.
+
+Pure: it returns bytes and never writes. `${workspace.file_path}` is the bundle variable that
+resolves to the synced files at deploy time, so the job finds the project and the manifest
+wherever the bundle lands.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Sequence
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Final
+
+from pipeloom.diagnostics import Report
+from pipeloom.plan.manifest import manifest_bytes
+from pipeloom.plan.model import Plan
+from pipeloom_databricks.jobs_model import to_json
+from pipeloom_databricks.render import (
+    Locations,
+    _own_version,
+    deploy_options,
+    job_name,
+    render_job,
+)
+from pipeloom_databricks.serialize import to_bundle_yaml
+
+BUNDLE_FILE: Final = "databricks.yml"
+WORKSPACE_FILES: Final = "${workspace.file_path}"
+
+
+@dataclass(frozen=True)
+class BundleFile:
+    path: Path
+    """Where the file goes: `<out>/<name>`."""
+    content: bytes
+
+
+@dataclass(frozen=True)
+class Runtime:
+    """What the target says that the job needs to know."""
+
+    artifacts_root: str | None
+    state_shared: bool
+    cancel_grace: int = 30
+
+
+def find_bundle_root(out: Path, explicit: Path | None) -> Path | None:
+    """`explicit`, else the nearest ancestor of `out` (itself included) that holds databricks.yml."""
+    if explicit is not None:
+        return explicit.resolve()
+    here = out.resolve()
+    for folder in (here, *here.parents):
+        if (folder / BUNDLE_FILE).is_file():
+            return folder
+    return None
+
+
+def relative_to_root(path: Path, root: Path) -> str | None:
+    """`path` below `root` as POSIX text (empty for the root itself), or None when outside."""
+    try:
+        rel = path.resolve().relative_to(root).as_posix()
+    except ValueError:
+        return None
+    return "" if rel == "." else rel
+
+
+def _workspace(rel: str) -> str:
+    return f"{WORKSPACE_FILES}/{rel}" if rel else WORKSPACE_FILES
+
+
+def render_bundle(
+    plan: Plan,
+    runtime: Runtime,
+    pipelines: Sequence[str],
+    *,
+    out: Path,
+    project_rel: str,
+    out_rel: str,
+    report: Report,
+) -> list[BundleFile] | None:
+    """The files of the given pipelines (all of them when empty), or None with the problems in
+    `report`. `project_rel` and `out_rel` are the project folder and the output folder relative
+    to the bundle root."""
+    opts = deploy_options(plan, report)
+    if opts is None:
+        return None
+    manifest = manifest_bytes(plan, stable=True)
+    files: list[BundleFile] = []
+    before = report.error_count
+    for pipeline in pipelines or sorted(opts.pipelines):
+        name = job_name(plan, pipeline)
+        locs = Locations(
+            project_root=_workspace(project_rel),
+            manifest_path=_workspace(f"{out_rel}/{name}.manifest.json".lstrip("/")),
+            artifacts_root=runtime.artifacts_root,
+            state_shared=runtime.state_shared,
+            cancel_grace=runtime.cancel_grace,
+        )
+        job = render_job(plan, pipeline, locs, report)
+        if job is None:
+            continue
+        header = (
+            f"Generated by pipeloom-databricks {_own_version(plan)}.\n"
+            f"Project: {plan.metadata.project}. Pipeline: {pipeline}. "
+            f"Target: {plan.metadata.target}.\n"
+            "Do not edit: run `pipeloom databricks bundle` again."
+        )
+        files.append(
+            BundleFile(out / f"{name}.job.yml", to_bundle_yaml(name, to_json(job.settings), header))
+        )
+        files.append(BundleFile(out / f"{name}.manifest.json", manifest))
+    return None if report.error_count > before else files