tinyfan 0.4.0__tar.gz → 0.5.0__tar.gz

tinyfan-0.5.0/PKG-INFO

@@ -0,0 +1,194 @@
+Metadata-Version: 2.5
+Name: tinyfan
+Version: 0.5.0
+Summary: Tiny Argo Workflows python devkit
+Project-URL: Documentation, https://github.com/eunchuldev/tinyfan#readme
+Project-URL: Issues, https://github.com/eunchuldev/tinyfan/issues
+Project-URL: Source, https://github.com/eunchuldev/tinyfan
+Author-email: eunchuldev <eunchulsong@gmail.com>
+Keywords: argo-workflow,pipeline,tinyfan,workflow
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Typing :: Typed
+Requires-Python: >=3.12
+Requires-Dist: croniter>=6.2.4
+Requires-Dist: pyyaml>=6.0.3
+Requires-Dist: typer-slim>=0.24.0
+Requires-Dist: tzdata
+Provides-Extra: all
+Requires-Dist: google-cloud-bigquery[pandas]; extra == 'all'
+Requires-Dist: google-cloud-storage; extra == 'all'
+Requires-Dist: networkx; extra == 'all'
+Requires-Dist: pandas; extra == 'all'
+Requires-Dist: pyarrow; extra == 'all'
+Provides-Extra: bigquery
+Requires-Dist: google-cloud-bigquery[pandas]; extra == 'bigquery'
+Requires-Dist: pandas; extra == 'bigquery'
+Requires-Dist: pyarrow; extra == 'bigquery'
+Provides-Extra: dev
+Requires-Dist: google-cloud-bigquery[pandas]; extra == 'dev'
+Requires-Dist: google-cloud-storage; extra == 'dev'
+Requires-Dist: jsonpatch>=1; extra == 'dev'
+Requires-Dist: jsonschema[format]; extra == 'dev'
+Requires-Dist: mypy>=1.14; extra == 'dev'
+Requires-Dist: networkx; extra == 'dev'
+Requires-Dist: pandas; extra == 'dev'
+Requires-Dist: pyarrow; extra == 'dev'
+Requires-Dist: pytest>=8.3.3; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Requires-Dist: types-croniter; extra == 'dev'
+Requires-Dist: types-jsonschema; extra == 'dev'
+Requires-Dist: types-networkx; extra == 'dev'
+Requires-Dist: types-pyyaml; extra == 'dev'
+Provides-Extra: gcs
+Requires-Dist: google-cloud-storage; extra == 'gcs'
+Provides-Extra: pandas
+Requires-Dist: pandas; extra == 'pandas'
+Requires-Dist: pyarrow; extra == 'pandas'
+Provides-Extra: viz
+Requires-Dist: networkx; extra == 'viz'
+Description-Content-Type: text/markdown
+
+# Tinyfan
+
+Tinyfan: Minimalist Data Pipeline Kit - Generate Argo Workflows with Python
+
+# Features
+
+* Generate Argo Workflows manifests from Python data pipeline definitions.
+* Ease of Use and highly extendable
+* Intuitive data model abstraction: let Argo handle orchestration—we focus on the data.
+* Argo Workflows is notably lightweight and powerful – and so are we!
+* Enhanced DevOps Experience: easly testable, Cloud Native and GitOps-ready.
+
+# Our Goal
+
+* **Minimize mental overhead** when building data pipelines.
+
+# Not Our Goal
+
+* **Full-featured orchestration framework:** We don't aim to be a battery-powered, comprehensive data pipeline orchestration solution.  
+  No databases, web servers, or controllers—just a data pipeline compiler. Let's Algo Workflows handle all the complexity.
+
+# Installation
+
+```
+# Requires Python 3.10+
+pipx install tinyfan
+```
+
+# Tiny Example
+
+```python
+# main.py
+
+# Asset definitions
+
+from tinyfan import asset
+
+
+@asset(schedule="*/3 * * * *")
+def world() -> str:
+    return "world"
+
+
+@asset()
+def greeting(world: str):
+    print("hello " + world)
+```
+
+```shell
+# Apply the changes to argo workflow
+
+tinyfan main.py | kubectl apply -f -
+```
+
+For a package, pass its directory or import name. Tinyfan statically discovers
+modules containing `@asset`, so unrelated submodules are not executed during
+manifest generation. Modules imported by an asset module (for example, a shared
+`Flow` definition) are loaded normally.
+
+```shell
+tinyfan src/my_package
+```
+
+Automatic package discovery requires statically recognizable Tinyfan `@asset`
+decorators. Dynamic asset registration and custom decorator wrappers are not
+automatically discovered.
+
+# Embedded source
+
+Embedded workflows unpack their source into temporary directories, so package
+data works with both `importlib.resources` and paths relative to `__file__`.
+Use `Path(__file__).parent` to locate data; the working directory is unchanged.
+
+Regular packages include their files and subdirectories, including extensionless
+data files. Embedding a nested module includes its top-level package. Standalone
+scripts include their containing directory so sibling imports and data files are
+available; keep scripts in a directory containing only files intended for the
+workflow. Git metadata, `.venv`/`venv`, Python bytecode, and common tool caches are
+excluded by default. Scripts execute as modules, preserving `__file__`, future
+imports, and runtime annotations; `if __name__ == "__main__"` blocks do not run.
+
+The embedding utilities accept `includes` and `excludes` glob patterns relative
+to the bundled directory (the top-level package for nested modules). Excluding a
+directory excludes its contents. Bundled imports take precedence over installed
+copies that have not already been imported. Temporary files are cleaned up on
+normal process exit, and unchanged source produces identical bundle bytes.
+
+Embedding does not resolve third-party dependencies or copy distribution metadata
+such as `.dist-info`. Install dependencies in the container image, including
+packages that need native libraries or `importlib.metadata`. Import-name embedding
+of a standalone module includes only its `.py` file; use a script path or regular
+package for accompanying data. Native libraries and namespace-package import
+names are rejected; use regular packages with `__init__.py`. Keep embedded source
+and data small because generated workflows carry them in an environment variable.
+
+# Runtime metadata
+
+Generated workflows read runtime metadata from the reserved `tinyfan-rundata`
+input artifact at `/tmp/tinyfan/input.json`. Parent metadata is transported as
+base64-encoded JSON, preserving datetime values and literal text through Argo
+parameter substitution. Asset functions and store APIs still receive ordinary
+Python values.
+
+After upgrading, regenerate and apply all workflow manifests together. The
+internal `rundata` output parameter now contains base64-encoded JSON, written to
+`/tmp/tinyfan/rundata.b64`; it is not compatible with the previous plain JSON
+transport. For packaged workflows, update the Tinyfan version in the container
+image as well.
+
+Intervals are calculated at runtime from the triggering workflow's cron schedule,
+timezone, and `workflow.scheduledTime`. If the workflow parameter `cronScheduleTime`
+is present, it takes precedence, supporting the timestamp supplied by
+`argo cron backfill` with its default `--argname`. Both RFC 3339 timestamps and the
+alpha CLI's Go-style timestamps (for example, `2026-03-09 00:00:00 -0400 EDT`)
+are accepted. Invalid or empty supplied values fail instead of falling back.
+The interval runs from the previous
+scheduled occurrence (inclusive) to the current one (exclusive), regardless of
+task delays or retries. Month lengths and leap years are calendar-based; missing
+DST times are skipped and repeated times are distinct occurrences.
+`data_interval_start` and `data_interval_end` are timezone-aware datetimes in the
+schedule's timezone. `ds` is the local start date and `ts` is its ISO timestamp
+including the UTC offset. All tasks in a workflow use that workflow's interval.
+
+Embedded workflows include croniter's required runtime modules and timezone data
+for the configured zones; no runtime download is needed. Regenerate manifests
+after timezone-data updates. Packaged images must install Tinyfan's dependencies,
+including croniter 6.2.4 or newer and `tzdata`.
+
+Backfill CLI compatibility is version-dependent: use a version supporting
+`spec.schedules` and the configured timezone. Older alpha implementations, such
+as Argo 3.7.0, only read the legacy `spec.schedule` field. Tinyfan does not add a
+duplicate `cronScheduleTime` default argument because the CLI appends it itself.
+
+# Real World Example (still tiny though!)
+
+Comming soon
+
+
+
+# License
+
+This project is licensed under the MIT License.

tinyfan-0.5.0/README.md

@@ -0,0 +1,142 @@
+# Tinyfan
+
+Tinyfan: Minimalist Data Pipeline Kit - Generate Argo Workflows with Python
+
+# Features
+
+* Generate Argo Workflows manifests from Python data pipeline definitions.
+* Ease of Use and highly extendable
+* Intuitive data model abstraction: let Argo handle orchestration—we focus on the data.
+* Argo Workflows is notably lightweight and powerful – and so are we!
+* Enhanced DevOps Experience: easly testable, Cloud Native and GitOps-ready.
+
+# Our Goal
+
+* **Minimize mental overhead** when building data pipelines.
+
+# Not Our Goal
+
+* **Full-featured orchestration framework:** We don't aim to be a battery-powered, comprehensive data pipeline orchestration solution.  
+  No databases, web servers, or controllers—just a data pipeline compiler. Let's Algo Workflows handle all the complexity.
+
+# Installation
+
+```
+# Requires Python 3.10+
+pipx install tinyfan
+```
+
+# Tiny Example
+
+```python
+# main.py
+
+# Asset definitions
+
+from tinyfan import asset
+
+
+@asset(schedule="*/3 * * * *")
+def world() -> str:
+    return "world"
+
+
+@asset()
+def greeting(world: str):
+    print("hello " + world)
+```
+
+```shell
+# Apply the changes to argo workflow
+
+tinyfan main.py | kubectl apply -f -
+```
+
+For a package, pass its directory or import name. Tinyfan statically discovers
+modules containing `@asset`, so unrelated submodules are not executed during
+manifest generation. Modules imported by an asset module (for example, a shared
+`Flow` definition) are loaded normally.
+
+```shell
+tinyfan src/my_package
+```
+
+Automatic package discovery requires statically recognizable Tinyfan `@asset`
+decorators. Dynamic asset registration and custom decorator wrappers are not
+automatically discovered.
+
+# Embedded source
+
+Embedded workflows unpack their source into temporary directories, so package
+data works with both `importlib.resources` and paths relative to `__file__`.
+Use `Path(__file__).parent` to locate data; the working directory is unchanged.
+
+Regular packages include their files and subdirectories, including extensionless
+data files. Embedding a nested module includes its top-level package. Standalone
+scripts include their containing directory so sibling imports and data files are
+available; keep scripts in a directory containing only files intended for the
+workflow. Git metadata, `.venv`/`venv`, Python bytecode, and common tool caches are
+excluded by default. Scripts execute as modules, preserving `__file__`, future
+imports, and runtime annotations; `if __name__ == "__main__"` blocks do not run.
+
+The embedding utilities accept `includes` and `excludes` glob patterns relative
+to the bundled directory (the top-level package for nested modules). Excluding a
+directory excludes its contents. Bundled imports take precedence over installed
+copies that have not already been imported. Temporary files are cleaned up on
+normal process exit, and unchanged source produces identical bundle bytes.
+
+Embedding does not resolve third-party dependencies or copy distribution metadata
+such as `.dist-info`. Install dependencies in the container image, including
+packages that need native libraries or `importlib.metadata`. Import-name embedding
+of a standalone module includes only its `.py` file; use a script path or regular
+package for accompanying data. Native libraries and namespace-package import
+names are rejected; use regular packages with `__init__.py`. Keep embedded source
+and data small because generated workflows carry them in an environment variable.
+
+# Runtime metadata
+
+Generated workflows read runtime metadata from the reserved `tinyfan-rundata`
+input artifact at `/tmp/tinyfan/input.json`. Parent metadata is transported as
+base64-encoded JSON, preserving datetime values and literal text through Argo
+parameter substitution. Asset functions and store APIs still receive ordinary
+Python values.
+
+After upgrading, regenerate and apply all workflow manifests together. The
+internal `rundata` output parameter now contains base64-encoded JSON, written to
+`/tmp/tinyfan/rundata.b64`; it is not compatible with the previous plain JSON
+transport. For packaged workflows, update the Tinyfan version in the container
+image as well.
+
+Intervals are calculated at runtime from the triggering workflow's cron schedule,
+timezone, and `workflow.scheduledTime`. If the workflow parameter `cronScheduleTime`
+is present, it takes precedence, supporting the timestamp supplied by
+`argo cron backfill` with its default `--argname`. Both RFC 3339 timestamps and the
+alpha CLI's Go-style timestamps (for example, `2026-03-09 00:00:00 -0400 EDT`)
+are accepted. Invalid or empty supplied values fail instead of falling back.
+The interval runs from the previous
+scheduled occurrence (inclusive) to the current one (exclusive), regardless of
+task delays or retries. Month lengths and leap years are calendar-based; missing
+DST times are skipped and repeated times are distinct occurrences.
+`data_interval_start` and `data_interval_end` are timezone-aware datetimes in the
+schedule's timezone. `ds` is the local start date and `ts` is its ISO timestamp
+including the UTC offset. All tasks in a workflow use that workflow's interval.
+
+Embedded workflows include croniter's required runtime modules and timezone data
+for the configured zones; no runtime download is needed. Regenerate manifests
+after timezone-data updates. Packaged images must install Tinyfan's dependencies,
+including croniter 6.2.4 or newer and `tzdata`.
+
+Backfill CLI compatibility is version-dependent: use a version supporting
+`spec.schedules` and the configured timezone. Older alpha implementations, such
+as Argo 3.7.0, only read the legacy `spec.schedule` field. Tinyfan does not add a
+duplicate `cronScheduleTime` default argument because the CLI appends it itself.
+
+# Real World Example (still tiny though!)
+
+Comming soon
+
+
+
+# License
+
+This project is licensed under the MIT License.

{tinyfan-0.4.0 → tinyfan-0.5.0}/examples/configs.py

@@ -1,5 +1,5 @@
 import tinyfan
-from tinyfan import ConfigMapRef, ConfigMapKeyRef, SecretRef, SecretKeyRef, cli_arg
+from tinyfan import ConfigMapKeyRef, ConfigMapRef, SecretKeyRef, SecretRef, cli_arg
 
 flow = tinyfan.Flow(
     name="configs",

{tinyfan-0.4.0 → tinyfan-0.5.0}/examples/getting-started.py

@@ -1,6 +1,7 @@
-import tinyfan
 from datetime import datetime
 
+import tinyfan
+
 
 @tinyfan.asset(
     schedule="*/1 * * * *",

{tinyfan-0.4.0 → tinyfan-0.5.0}/examples/packaged/src/tinyfan_examples_packaged/asset.py

@@ -1,6 +1,7 @@
-import tinyfan
 from datetime import datetime
 
+import tinyfan
+
 
 @tinyfan.asset(
     schedule="*/1 * * * *", container={"image": "tinyfan-examples-packaged:local", "imagePullPolicy": "Never"}

{tinyfan-0.4.0 → tinyfan-0.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tinyfan"
-version = "0.4.0"
+version = "0.5.0"
 description = 'Tiny Argo Workflows python devkit'
 readme = "README.md"
 requires-python = ">=3.12"
@@ -12,7 +12,7 @@ classifiers = [
   "Programming Language :: Python :: 3.12",
   "Typing :: Typed",
 ]
-dependencies = ["croniter>=6", "pyyaml>=6.0.3", "typer-slim>=0.24.0"]
+dependencies = ["croniter>=6.2.4", "pyyaml>=6.0.3", "typer-slim>=0.24.0", "tzdata"]
 
 [project.scripts]
 tinyfan = "tinyfan.cli:main"

{tinyfan-0.4.0 → tinyfan-0.5.0}/src/tinyfan/__init__.py

@@ -1,19 +1,19 @@
-from .flow import Flow, Asset, asset
+from .config import ConfigMapKeyRef, ConfigMapRef, SecretKeyRef, SecretRef, cli_arg
+from .flow import Asset, Flow, asset
+from .resources.base import ResourceBase
 from .stores.base import StoreBase
 from .stores.naive import NaiveStore
-from .config import ConfigMapRef, ConfigMapKeyRef, SecretRef, SecretKeyRef, cli_arg
-from .resources.base import ResourceBase
 
 __all__ = [
-    "Flow",
     "Asset",
-    "asset",
-    "StoreBase",
-    "NaiveStore",
-    "ConfigMapRef",
     "ConfigMapKeyRef",
-    "SecretRef",
+    "ConfigMapRef",
+    "Flow",
+    "NaiveStore",
+    "ResourceBase",
     "SecretKeyRef",
+    "SecretRef",
+    "StoreBase",
+    "asset",
     "cli_arg",
-    "ResourceBase",
 ]

{tinyfan-0.4.0 → tinyfan-0.5.0}/src/tinyfan/argo_typing.py

@@ -1,4 +1,4 @@
-from typing import Any, TypedDict, NotRequired
+from typing import Any, NotRequired, TypedDict
 
 
 class ExecAction(TypedDict):

{tinyfan-0.4.0 → tinyfan-0.5.0}/src/tinyfan/cli.py

@@ -1,6 +1,7 @@
+from typing import Annotated
+
 import typer
 
-from typing_extensions import Annotated
 from .codegen import codegen
 from .config import CLI_CONFIG_STATE
 
@@ -9,10 +10,6 @@ def tinyfan(
     location: str,
     embedded: bool | None = None,
     arg: Annotated[list[str] | None, typer.Option(metavar="KEY=VALUE")] = None,
-    import_all: Annotated[
-        bool,
-        typer.Option(help="Import every submodule instead of discovering modules with @asset statically."),
-    ] = False,
 ):
     """
     Generate argocd workflow resource as yaml from tinyfan definitions
@@ -20,9 +17,9 @@ def tinyfan(
     if arg is not None:
         CLI_CONFIG_STATE.cli_args.update({k: v for (k, v) in (val.split("=") for val in arg)})
     if location.endswith(".py"):
-        print(codegen(location=location, embedded=embedded or True, import_all=import_all))
+        print(codegen(location=location, embedded=embedded or True))
     else:
-        print(codegen(location=location, embedded=embedded or False, import_all=import_all))
+        print(codegen(location=location, embedded=embedded or False))
 
 
 def main():