streamwright-spark 0.1.0__tar.gz

streamwright_spark-0.1.0/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.

streamwright_spark-0.1.0/PKG-INFO

@@ -0,0 +1,107 @@
+Metadata-Version: 2.4
+Name: streamwright-spark
+Version: 0.1.0
+Summary: Spark jobs for StreamWright (kind: SparkJob), attached as `sw spark ...`.
+Author-email: Karthick Jaganathan <kjaganathan.sde@gmail.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://streamwright.web.app
+Project-URL: Documentation, https://streamwright.web.app/docs/
+Project-URL: Repository, https://github.com/karthick-jaganathan/streamwright-spark
+Project-URL: Issue Tracker, https://github.com/karthick-jaganathan/streamwright-spark/issues
+Keywords: data,pipeline,etl,spark,pyspark,deltalake,kafka,sqs,yaml,streamwright
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Database
+Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pyyaml==6.0.2
+Requires-Dist: streamwright~=0.1.9
+Provides-Extra: spark
+Requires-Dist: pyspark<3.6,>=3.5; extra == "spark"
+Provides-Extra: delta
+Requires-Dist: delta-spark<3.3,>=3.2; extra == "delta"
+Provides-Extra: postgres
+Requires-Dist: psycopg[binary]>=3.1; extra == "postgres"
+Provides-Extra: kafka
+Requires-Dist: confluent-kafka>=2.4; extra == "kafka"
+Requires-Dist: aws-msk-iam-sasl-signer-python>=1.0; extra == "kafka"
+Provides-Extra: sqs
+Requires-Dist: boto3>=1.34; extra == "sqs"
+Provides-Extra: emr
+Requires-Dist: boto3>=1.34; extra == "emr"
+Provides-Extra: test
+Requires-Dist: pytest>=8; extra == "test"
+Requires-Dist: jsonschema>=4; extra == "test"
+Provides-Extra: all
+Requires-Dist: pyspark<3.6,>=3.5; extra == "all"
+Requires-Dist: delta-spark<3.3,>=3.2; extra == "all"
+Requires-Dist: psycopg[binary]>=3.1; extra == "all"
+Requires-Dist: confluent-kafka>=2.4; extra == "all"
+Requires-Dist: aws-msk-iam-sasl-signer-python>=1.0; extra == "all"
+Requires-Dist: boto3>=1.34; extra == "all"
+Dynamic: license-file
+
+# StreamWright Spark
+
+[![PyPI](https://img.shields.io/pypi/v/streamwright-spark.svg)](https://pypi.org/project/streamwright-spark/)
+[![Python](https://img.shields.io/pypi/pyversions/streamwright-spark.svg)](https://pypi.org/project/streamwright-spark/)
+[![License](https://img.shields.io/pypi/l/streamwright-spark.svg)](https://pypi.org/project/streamwright-spark/)
+[![Docs](https://img.shields.io/badge/docs-streamwright.web.app-brightgreen.svg)](https://streamwright.web.app/docs/spark/overview/)
+
+`kind: SparkJob` for [StreamWright](https://pypi.org/project/streamwright/): declarative batch pipelines on Apache Spark.
+
+- **Read and write** object storage, Delta Lake, databases, Kafka and SQS with StreamWright connectors.
+- **Exactly-once batches**: batch state, leases and output receipts; replay-safe writes.
+- **Any source connector** (REST APIs, ads platforms) through driver-side call steps.
+- **Runs** locally, on Spark standalone and on AWS EMR on EC2.
+
+## Install
+
+```bash
+pip install "streamwright-spark[spark]"    # needs Java 11+
+sw connectors -i files
+```
+
+## Example
+
+```yaml
+# orders.yaml
+kind: SparkJob
+version: 1
+name: daily_orders
+connections:
+  lake: {provider: files, roots: ["/data/lake/"]}
+steps:
+  - name: orders
+    connection: lake
+    service: object
+    method: read
+    arguments: {path: "raw/orders/*.csv", format: csv, options: {header: true}}
+  - name: daily_totals
+    sql: SELECT CAST(ordered_at AS DATE) AS day, COUNT(*) AS orders FROM orders GROUP BY 1
+outputs:
+  - name: save_totals
+    connection: lake
+    service: object
+    method: write
+    arguments: {path: "/data/lake/curated/daily_totals/", format: parquet, mode: overwrite}
+    sql: SELECT * FROM daily_totals
+runtime:
+  state: {sqlite: /data/state/daily_orders.db}
+  platform: {type: local}
+```
+
+```bash
+sw spark validate orders.yaml
+sw spark run orders.yaml --once
+```
+
+## Links
+
+[Documentation](https://streamwright.web.app/docs/spark/overview/) ·
+[StreamWright](https://github.com/karthick-jaganathan/streamwright)

streamwright_spark-0.1.0/README.md

@@ -0,0 +1,59 @@
+# StreamWright Spark
+
+[![PyPI](https://img.shields.io/pypi/v/streamwright-spark.svg)](https://pypi.org/project/streamwright-spark/)
+[![Python](https://img.shields.io/pypi/pyversions/streamwright-spark.svg)](https://pypi.org/project/streamwright-spark/)
+[![License](https://img.shields.io/pypi/l/streamwright-spark.svg)](https://pypi.org/project/streamwright-spark/)
+[![Docs](https://img.shields.io/badge/docs-streamwright.web.app-brightgreen.svg)](https://streamwright.web.app/docs/spark/overview/)
+
+`kind: SparkJob` for [StreamWright](https://pypi.org/project/streamwright/): declarative batch pipelines on Apache Spark.
+
+- **Read and write** object storage, Delta Lake, databases, Kafka and SQS with StreamWright connectors.
+- **Exactly-once batches**: batch state, leases and output receipts; replay-safe writes.
+- **Any source connector** (REST APIs, ads platforms) through driver-side call steps.
+- **Runs** locally, on Spark standalone and on AWS EMR on EC2.
+
+## Install
+
+```bash
+pip install "streamwright-spark[spark]"    # needs Java 11+
+sw connectors -i files
+```
+
+## Example
+
+```yaml
+# orders.yaml
+kind: SparkJob
+version: 1
+name: daily_orders
+connections:
+  lake: {provider: files, roots: ["/data/lake/"]}
+steps:
+  - name: orders
+    connection: lake
+    service: object
+    method: read
+    arguments: {path: "raw/orders/*.csv", format: csv, options: {header: true}}
+  - name: daily_totals
+    sql: SELECT CAST(ordered_at AS DATE) AS day, COUNT(*) AS orders FROM orders GROUP BY 1
+outputs:
+  - name: save_totals
+    connection: lake
+    service: object
+    method: write
+    arguments: {path: "/data/lake/curated/daily_totals/", format: parquet, mode: overwrite}
+    sql: SELECT * FROM daily_totals
+runtime:
+  state: {sqlite: /data/state/daily_orders.db}
+  platform: {type: local}
+```
+
+```bash
+sw spark validate orders.yaml
+sw spark run orders.yaml --once
+```
+
+## Links
+
+[Documentation](https://streamwright.web.app/docs/spark/overview/) ·
+[StreamWright](https://github.com/karthick-jaganathan/streamwright)

streamwright_spark-0.1.0/pyproject.toml

@@ -0,0 +1,74 @@
+[build-system]
+requires = ["setuptools>=61.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "streamwright-spark"
+version = "0.1.0"
+description = "Spark jobs for StreamWright (kind: SparkJob), attached as `sw spark ...`."
+readme = "README.md"
+license = "Apache-2.0"
+authors = [
+    {name = "Karthick Jaganathan", email = "kjaganathan.sde@gmail.com"},
+]
+keywords = ["data", "pipeline", "etl", "spark", "pyspark", "deltalake", "kafka", "sqs", "yaml", "streamwright"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Database",
+    "Topic :: Software Development :: Libraries :: Application Frameworks",
+]
+requires-python = ">=3.11"
+# Validation, planning, naming, the state store and the batch loop need only the standard library, PyYAML and
+# streamwright (core), so `sw spark validate` runs without Spark. The connectors themselves come from the hub:
+# `streamwright connectors install s3 postgres deltalake kafka sqs ...`. Everything else is an extra.
+dependencies = ["pyyaml==6.0.2", "streamwright~=0.1.9"]
+
+[project.urls]
+Homepage = "https://streamwright.web.app"
+Documentation = "https://streamwright.web.app/docs/"
+Repository = "https://github.com/karthick-jaganathan/streamwright-spark"
+"Issue Tracker" = "https://github.com/karthick-jaganathan/streamwright-spark/issues"
+
+[project.optional-dependencies]
+spark    = ["pyspark>=3.5,<3.6"]
+delta    = ["delta-spark>=3.2,<3.3"]
+postgres = ["psycopg[binary]>=3.1"]
+kafka    = ["confluent-kafka>=2.4", "aws-msk-iam-sasl-signer-python>=1.0"]
+sqs      = ["boto3>=1.34"]
+emr      = ["boto3>=1.34"]
+test     = ["pytest>=8", "jsonschema>=4"]
+all      = ["pyspark>=3.5,<3.6", "delta-spark>=3.2,<3.3", "psycopg[binary]>=3.1", "confluent-kafka>=2.4",
+            "aws-msk-iam-sasl-signer-python>=1.0", "boto3>=1.34"]
+
+[project.scripts]
+streamwright-spark = "streamwright.spark.cli:main"
+sw-spark = "streamwright.spark.cli:main"
+
+[project.entry-points."streamwright.job_kinds"]
+SparkJob = "streamwright.spark.plugin:JOB_ENGINE"
+
+[project.entry-points."streamwright.commands"]
+spark = "streamwright.spark.cli:register"
+
+[project.entry-points."streamwright.spark.launchers"]
+local = "streamwright.spark.launchers.local:LocalLauncher"
+standalone = "streamwright.spark.launchers.standalone:StandaloneLauncher"
+emr_ec2 = "streamwright.spark.launchers.emr_ec2:EmrEc2Launcher"
+
+[tool.setuptools]
+# `streamwright` is a namespace package shared with streamwright (core) and its connector distributions
+package-dir = {"" = "src"}
+packages = [
+  "streamwright.spark", "streamwright.spark.cli", "streamwright.spark.contracts",
+  "streamwright.spark.engine", "streamwright.spark.job",
+  "streamwright.spark.launchers", "streamwright.spark.plan", "streamwright.spark.runtime",
+  "streamwright.spark.storage", "streamwright.spark.sdk", "streamwright.spark.io"
+]
+
+[tool.setuptools.package-data]
+"streamwright.spark.sdk" = ["py.typed"]
+"streamwright.spark" = ["guide.md"]

streamwright_spark-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

streamwright_spark-0.1.0/src/streamwright/spark/__init__.py

@@ -0,0 +1 @@
+"""SparkJob engine for StreamWright."""

streamwright_spark-0.1.0/src/streamwright/spark/cli/__init__.py

@@ -0,0 +1,14 @@
+"""The `sw spark` command line."""
+
+import argparse
+
+from streamwright.spark.cli.main import main
+
+__all__ = ["main", "register"]
+
+
+def register(subparsers):
+    parser = subparsers.add_parser("spark", help="validate, run and inspect SparkJob pipelines", add_help=False)
+    parser.add_argument("-h", "--help", action="store_true")
+    parser.add_argument("arguments", nargs=argparse.REMAINDER)
+    parser.set_defaults(command_handler=lambda args: main(["--help"] if args.help else args.arguments))

streamwright_spark-0.1.0/src/streamwright/spark/cli/__main__.py

@@ -0,0 +1,7 @@
+"""python -m streamwright.spark.cli"""
+
+import sys
+
+from streamwright.spark.cli.main import main
+
+sys.exit(main())

streamwright_spark-0.1.0/src/streamwright/spark/cli/aws_secrets.py

@@ -0,0 +1,58 @@
+"""AWS Secrets Manager access, imported only by the driver when configured."""
+
+import json
+import re
+
+import boto3
+
+
+def read_secrets(source, job):
+    region = ((job.get("runtime") or {}).get("platform") or {}).get("region")
+    client = boto3.client("secretsmanager", region_name=region)
+    data = {}
+
+    def fetch_value(secret_id):
+        reply = client.get_secret_value(SecretId=secret_id)
+        raw = reply.get("SecretString")
+        if raw is None and "SecretBinary" in reply:
+            raw = reply["SecretBinary"].decode("utf-8")
+        return raw or ""
+
+    mapping = source.get("mapping")
+    if isinstance(mapping, dict):
+        for variable, secret_id in mapping.items():
+            raw = fetch_value(secret_id)
+            try:
+                parsed = json.loads(raw)
+                if isinstance(parsed, dict):
+                    if variable in parsed:
+                        data[variable] = parsed[variable]
+                    elif len(parsed) == 1:
+                        data[variable] = next(iter(parsed.values()))
+                    else:
+                        data.update(parsed)
+                else:
+                    data[variable] = raw
+            except (ValueError, TypeError):
+                data[variable] = raw
+
+    secret_ids = source.get("ids") or source.get("id")
+    if isinstance(secret_ids, str):
+        secret_ids = [secret_ids]
+    elif not isinstance(secret_ids, (list, tuple)):
+        secret_ids = []
+    for secret_id in secret_ids:
+        raw = fetch_value(secret_id)
+        try:
+            parsed = json.loads(raw)
+            if isinstance(parsed, dict):
+                data.update(parsed)
+            else:
+                leaf = secret_id.split("/")[-1].split(":")[-1]
+                leaf = re.sub(r"-[A-Za-z0-9]{6}$", "", leaf)
+                data[leaf] = raw
+        except (ValueError, TypeError):
+            leaf = secret_id.split("/")[-1].split(":")[-1]
+            leaf = re.sub(r"-[A-Za-z0-9]{6}$", "", leaf)
+            data[leaf] = raw
+    return data

streamwright_spark-0.1.0/src/streamwright/spark/cli/common.py

@@ -0,0 +1,73 @@
+"""Pieces shared by the sw spark commands."""
+
+import sys
+
+from streamwright.core.jobs.inputs import InputError as InputsError
+from streamwright.core.jobs.inputs import parse_set
+from streamwright.core.sdk.contract import resolve_connection
+from streamwright.spark.contracts import Connection
+from streamwright.spark.runtime import registry
+
+__all__ = ["InputsError", "add_job_arguments", "connections_of", "err", "load_plugins", "parse_set"]
+
+
+def err(text):
+    sys.stderr.write(text + "\n")
+
+
+def add_job_arguments(parser, many=False):
+    if many:
+        parser.add_argument("job", nargs="*", metavar="PATH", help="path to the job definition YAML file(s)")
+        parser.add_argument(
+            "--job",
+            "-j",
+            action="append",
+            default=[],
+            dest="flag_jobs",
+            help="path to the job definition YAML file (can be specified multiple times)",
+        )
+        parser.add_argument("--file", "-f", action="append", default=[], dest="flag_files", help="alias for --job")
+        parser.add_argument("--pipeline", action="append", default=[], dest="flag_pipelines", help="alias for --job")
+    else:
+        parser.add_argument("job", nargs="?", metavar="JOB", help="path to the job definition YAML file or directory")
+        parser.add_argument("--job", "-j", dest="flag_job", help="path to the job definition YAML file or directory")
+        parser.add_argument("--file", "-f", dest="flag_file", help="alias for --job")
+        parser.add_argument("--pipeline", dest="flag_pipeline", help="alias for --job")
+    parser.add_argument("--config", help="a YAML file with a `config:` mapping (values for spec.config)")
+    parser.add_argument(
+        "--set",
+        action="append",
+        default=[],
+        metavar="NAME=VALUE",
+        help="override a spec.config value (e.g. --set key=value)",
+    )
+    parser.add_argument("--overlay", action="append", default=[], help="YAML merged over the job; a null deletes a key")
+    parser.add_argument(
+        "--allow-connector", action="append", default=None, metavar="PROVIDER", help="only load these providers"
+    )
+
+
+def load_plugins(allow=None):
+    """({provider: adapter}, {platform: launcher}, problems)."""
+    adapters, problems = registry.load_all("adapter", allow)
+    launchers, more = registry.load_all("launcher")
+    return adapters, launchers, problems + more
+
+
+def connections_of(job, *, adapters=None, declared=None, config=None, secrets=None):
+    """
+    {name: Connection} of the connections the Spark engine runs natively (a Spark adapter): `provider` apart, the rest
+    is the auth block. A provider without a Spark adapter is reached only through call steps, which resolve its
+    connection in the source engine.
+    """
+    connections = {}
+    for name, connection in (job.get("connections") or {}).items():
+        provider = connection["provider"]
+        adapter = (adapters or {}).get(provider)
+        if adapter is None:
+            continue
+        original = (declared or job)["connections"][name]
+        auth = {key: value for key, value in original.items() if key != "provider"}
+        values = resolve_connection(adapter.definition, auth, config=config or {}, secrets=secrets or {})
+        connections[name] = Connection(name, provider, values)
+    return connections

streamwright_spark-0.1.0/src/streamwright/spark/cli/inputs.py

@@ -0,0 +1,40 @@
+"""Config and secret values for a run, through core input handling."""
+
+from importlib import import_module
+
+from streamwright.core.config import inputs as core_inputs
+from streamwright.core.jobs import inputs as job_inputs
+from streamwright.spark.cli.common import err, parse_set
+
+__all__ = ["InputError", "config_values", "secret_values"]
+
+InputError = core_inputs.InputError
+
+
+def config_values(job, args):
+    provided = {}
+    if args.config:
+        provided.update(job_inputs.read_config_values(args.config))
+    provided.update(parse_set(args.set))
+    return job_inputs.effective_config(job, provided)
+
+
+def secret_values(job, args):
+    """STREAMWRIGHT_SECRET_<NAME> variables, --secrets FILE, or runtime.secrets (AWS Secrets Manager); never printed."""
+    declared = ((job.get("spec") or {}).get("secrets")) or {}
+    provided = {}
+    if getattr(args, "secrets", None):
+        provided.update(core_inputs.read_values_file(args.secrets, err))
+    for name, value in core_inputs.secrets_from_env(list(declared)).items():
+        provided.setdefault(name, value)
+    source = (job.get("runtime") or {}).get("secrets") or {}
+    if source.get("source") == "aws_secretsmanager" and len(set(provided) & set(declared)) < len(declared):
+        try:
+            aws_secrets = import_module("streamwright.spark.cli.aws_secrets")
+        except ImportError as exc:
+            if exc.name != "boto3":
+                raise
+            raise InputError('boto3 is not installed; pip install "streamwright-spark[emr]"') from exc
+        for name, value in aws_secrets.read_secrets(source, job).items():
+            provided.setdefault(name, value)
+    return job_inputs.secret_values(job, provided)