dbt-confluent 0.1.0__tar.gz

dbt_confluent-0.1.0/.github/CODEOWNERS

@@ -0,0 +1 @@
+*	@confluentinc/pyflink

dbt_confluent-0.1.0/.gitignore

@@ -0,0 +1,133 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+test.env
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+# .python-version is tracked in git for project-wide version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# uv
+# uv.lock should be committed to version control
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

dbt_confluent-0.1.0/.python-version

@@ -0,0 +1 @@
+3.11

dbt_confluent-0.1.0/.semaphore/publish_to_pypi.yml

@@ -0,0 +1,23 @@
+
+version: v1.0
+name: Publish `dbt_confluent` to PyPi
+agent:
+  machine:
+    type: s1-prod-ubuntu24-04-amd64-1
+
+global_job_config:
+  prologue:
+    commands:
+      - checkout
+      - . vault-setup
+      - curl -LsSf https://astral.sh/uv/install.sh | sh
+
+blocks:
+  - name: Publish `dbt_confluent` to PyPi
+    task:
+      jobs:
+        - name: Publish `dbt_confluent` to PyPi
+          commands:
+            - DBT_CONFLUENT_KEY=$(vault kv get -field=dbt-confluent v1/ci/kv/pypi/pypi.org)
+            - uv build
+            - uv publish -u __token__ -p "$DBT_CONFLUENT_KEY" dist/*

dbt_confluent-0.1.0/.semaphore/semaphore.yml

@@ -0,0 +1,83 @@
+version: v1.0
+name: build-test-release
+agent:
+  machine:
+    type: s1-prod-ubuntu24-04-amd64-1
+
+auto_cancel:
+  running:
+    when: "branch != 'main'"
+
+execution_time_limit:
+  hours: 1
+
+queue:
+  - when: "branch != 'main'"
+    processing: parallel
+
+global_job_config:
+  prologue:
+    commands:
+      - checkout
+      - . vault-setup
+      - git submodule update --init
+      - curl -LsSf https://astral.sh/uv/install.sh | sh
+      - uv sync --extra dev --extra test
+
+blocks:
+  - name: "Lint"
+    dependencies: []
+    task:
+      jobs:
+        - name: "Ruff Check"
+          commands:
+            - uv run ruff check dbt/ tests/
+        - name: "Ruff Format Check"
+          commands:
+            - uv run ruff format --check dbt/ tests/
+
+  - name: "Build"
+    dependencies: []
+    task:
+      jobs:
+        - name: "Build Package"
+          commands:
+            - uv build
+            # Install it locally and check that it can be imported.
+            # Clean the venv created in the prologue first
+            - uv venv --clear
+            - uv pip install dist/dbt_confluent-*.whl
+            - uv run python -c "import confluent_sql; import dbt.adapters.confluent; print('OK')"
+
+  - name: "Test"
+    dependencies:
+      - "Lint"
+      - "Build"
+    task:
+      jobs:
+        - name: "Run Tests"
+          commands:
+            - |
+              if [ -z "${CONFLUENT_FLINK_API_KEY:-}" ]; then
+                echo "CONFLUENT_FLINK_API_KEY not set, skipping tests"
+              else
+                uv run pytest --junitxml=test-results.xml
+              fi
+      epilogue:
+        always:
+          commands:
+            - |
+              if [[ -f test-results.xml ]]; then
+                test-results publish test-results.xml
+              fi
+
+after_pipeline:
+  task:
+    jobs:
+      - name: Publish Test Results to Semaphore
+        commands:
+          - test-results gen-pipeline-report || echo "Could not publish pipeline test result report. Are there any test results to publish?"
+
+promotions:
+  - name: Publish dbt-confluent to PyPi
+    pipeline_file: publish_to_pypi.yml

dbt_confluent-0.1.0/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
+

dbt_confluent-0.1.0/MANIFEST.in

@@ -0,0 +1 @@
+recursive-include dbt/include *.sql *.yml *.md

dbt_confluent-0.1.0/MATERIALIZATIONS.md

@@ -0,0 +1,19 @@
+# Materializations
+
+## Supported
+
+| Materialization | Description |
+|---|---|
+| `table` | Creates a table via `CREATE TABLE ... AS SELECT` (CTAS). Runs in snapshot mode — the query executes once and completes. Requires `--full-refresh` to replace an existing table. |
+| `view` | Drop-and-recreate view. |
+| `materialized_view` | Creates a Flink table via CTAS that is continuously updated by Flink. No manual refresh needed. Note: despite the dbt name, this creates a Flink table with a continuous query, not a traditional database materialized view. |
+| `streaming_table` | Creates a table then runs a separate continuous `INSERT INTO ... SELECT` statement. This two-statement approach is currently the preferred way to build streaming pipelines (until Flink's materialized table feature reaches GA). Supports table options via `config(with={...})`. Requires `--full-refresh` to replace an existing table. |
+| `streaming_source` | Creates a connector-backed source table (e.g., Datagen). Requires `config(connector='...')`. The model SQL defines the column definitions. Supports additional connector options via `config(with={...})`. Requires `--full-refresh` to replace an existing table. See the [Confluent connector catalog](https://docs.confluent.io/cloud/current/connectors/index.html) and [Flink CREATE TABLE documentation](https://docs.confluent.io/cloud/current/flink/reference/statements/create-table.html) for available connectors and options. |
+| `ephemeral` | Standard dbt CTE-based query fragment, not materialized in Flink. |
+
+## Not Supported
+
+| Materialization | Reason |
+|---|---|
+| `incremental` | dbt's batch-incremental semantics does not map to Flink's continuous processing model. Use `streaming_table` instead. |
+| `snapshot` | Flink SQL lacks the batch operations (MERGE, UPDATE) required by dbt snapshots. |

dbt_confluent-0.1.0/PKG-INFO

@@ -0,0 +1,192 @@
+Metadata-Version: 2.4
+Name: dbt-confluent
+Version: 0.1.0
+Summary: The Confluent Cloud adapter plugin for DBT
+Project-URL: Homepage, https://github.com/confluentinc/dbt-confluent
+Project-URL: Repository, https://github.com/confluentinc/dbt-confluent
+Author-email: Confluent <dev@confluent.io>
+Maintainer-email: Confluent <dev@confluent.io>
+License: Apache-2.0
+License-File: LICENSE
+Keywords: adapter,cloud,confluent,dbt
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10.0
+Requires-Dist: agate~=1.0
+Requires-Dist: confluent-sql~=0.1
+Requires-Dist: dbt-adapters~=1.16
+Requires-Dist: dbt-common~=1.12
+Requires-Dist: dbt-core~=1.11
+Requires-Dist: httpx<0.29.0,>=0.23.0
+Provides-Extra: dev
+Requires-Dist: ipdb>=0.13.0; extra == 'dev'
+Requires-Dist: mypy>=1.13.0; extra == 'dev'
+Requires-Dist: pre-commit>=4.0.0; extra == 'dev'
+Requires-Dist: ruff>=0.8.0; extra == 'dev'
+Provides-Extra: test
+Requires-Dist: dbt-tests-adapter>=1.10; extra == 'test'
+Requires-Dist: pytest-dotenv>=0.5.2; extra == 'test'
+Requires-Dist: pytest>=8.4.2; extra == 'test'
+Description-Content-Type: text/markdown
+
+# dbt-confluent
+
+The [dbt](https://www.getdbt.com/) adapter for [Confluent Cloud](https://confluent.io/confluent-cloud/) Flink SQL.
+
+Build, test, and manage streaming data transformations on Confluent Cloud using dbt's familiar development workflow.
+
+## Overview
+
+`dbt-confluent` lets you use dbt to define and run SQL transformations on Confluent Cloud's fully managed Apache Flink service. It supports both batch-style and streaming materializations, enabling continuous data pipelines defined as dbt models.
+
+Features:
+- Standard dbt materializations (table, view, ephemeral) adapted for Flink SQL
+- Streaming-native materializations (`streaming_table`, `streaming_source`) for continuous data pipelines
+- Materialized views powered by Flink's continuous query execution
+- Integration with Confluent Cloud connectors (e.g., Datagen/Faker) via `streaming_source`
+
+See [Materializations](MATERIALIZATIONS.md) for the full list and details.
+
+## Installation
+
+```bash
+pip install dbt-confluent
+```
+
+or with [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv add dbt-confluent
+```
+
+Requires Python 3.10+.
+
+## Configuration
+
+After installing, scaffold a new project with:
+
+```bash
+dbt init my_project
+```
+
+Select `confluent` as the adapter and fill in the prompts for your Confluent Cloud credentials (API key, compute pool, environment, etc.).
+
+### Concept mapping
+
+Confluent Cloud Flink uses different terminology than traditional databases. Here's how dbt concepts map to Flink and Confluent Cloud:
+
+| dbt concept | Flink concept | Confluent Cloud entity |
+|---|---|---|
+| `database` | Catalog | Environment |
+| `schema` | Database | Kafka cluster |
+
+### Schema configuration
+
+Unlike most dbt adapters, `dbt-confluent` cannot create or drop schemas — a dbt schema maps to a Flink database (Kafka cluster) in Confluent Cloud, which is managed externally. Both the `dbname` in your `profiles.yml` and any model-level `schema` config must reference an existing Flink database by name:
+
+```yaml
+# dbt_project.yml
+models:
+  my_project:
+    +schema: my-kafka-cluster
+```
+
+## Usage
+
+### Streaming table
+
+A streaming table creates a table and runs a continuous INSERT query against it:
+
+```sql
+-- models/pageviews_enriched.sql
+{{
+  config(
+    materialized='streaming_table',
+    with={'changelog.mode': 'append'}
+  )
+}}
+
+SELECT
+  p.user_id,
+  p.page_url,
+  u.username
+FROM {{ ref('pageviews') }} p
+JOIN {{ ref('users') }} u ON p.user_id = u.user_id
+```
+
+### Streaming source
+
+A streaming source creates a connector-backed source table. The model SQL defines the column definitions:
+
+```sql
+-- models/datagen_users.sql
+{{
+  config(
+    materialized='streaming_source',
+    connector='faker',
+    with={'rows-per-second': '10'}
+  )
+}}
+
+`user_id` INT,
+`username` STRING,
+`email` STRING
+```
+
+See [Materializations](MATERIALIZATIONS.md) for the full list and details.
+
+## Known Limitations
+
+- **No schema management**: Flink databases (Kafka clusters) cannot be created or dropped — they are managed in Confluent Cloud.
+- **No table renames**: `ALTER TABLE RENAME` is not supported; to effectively rename a model you must drop and recreate the underlying table, which for `table`, `streaming_table`, and `streaming_source` materializations requires running with `--full-refresh`.
+- **No transactions**: Flink SQL is non-transactional.
+- **No snapshots**: Flink SQL lacks the batch operations (MERGE, UPDATE) required by dbt snapshots.
+- **No incremental**: dbt's batch-incremental semantics does not map to Flink's continuous processing model. Use `streaming_table` instead.
+
+## Development
+
+```bash
+git clone https://github.com/confluentinc/dbt-confluent
+cd dbt-confluent
+uv sync --extra dev --extra test
+```
+
+### Code quality
+
+```bash
+uv run ruff check dbt/ tests/
+uv run ruff format --check dbt/ tests/
+```
+
+### Running tests
+
+Tests require a Confluent Cloud environment. Set the following environment variables (or add them to a `test.env` file):
+
+```bash
+export CONFLUENT_ENV_ID=env-xxxxxx
+export CONFLUENT_ORG_ID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
+export CONFLUENT_COMPUTE_POOL_ID=lfcp-xxxxx
+export CONFLUENT_CLOUD_PROVIDER=aws
+export CONFLUENT_CLOUD_REGION=us-west-6
+export CONFLUENT_TEST_DBNAME=dbname
+export CONFLUENT_FLINK_API_KEY=xxx
+export CONFLUENT_FLINK_API_SECRET=xxx
+```
+
+```bash
+uv run pytest
+```
+
+## Versioning
+
+This adapter follows [semantic versioning](https://semver.org/) and is versioned independently from dbt Core. Compatibility with dbt Core is declared via dependencies (currently requires `dbt-core~=1.11`).
+
+## License
+
+Apache-2.0 — see [LICENSE](./LICENSE) for details.