ddeutil-workflow 0.0.5__tar.gz → 0.0.6__tar.gz

{ddeutil_workflow-0.0.5/src/ddeutil_workflow.egg-info → ddeutil_workflow-0.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddeutil-workflow
-Version: 0.0.5
+Version: 0.0.6
 Summary: Data Developer & Engineer Workflow Utility Objects
 Author-email: ddeutils <korawich.anu@gmail.com>
 License: MIT
@@ -24,30 +24,32 @@ License-File: LICENSE
 Requires-Dist: fmtutil
 Requires-Dist: ddeutil-io
 Requires-Dist: python-dotenv==1.0.1
-Requires-Dist: schedule==1.2.2
+Provides-Extra: app
+Requires-Dist: fastapi==0.112.0; extra == "app"
+Requires-Dist: apscheduler[sqlalchemy]==3.10.4; extra == "app"
 
-# Data Utility: _Workflow_
+# Workflow
 
 [![test](https://github.com/ddeutils/ddeutil-workflow/actions/workflows/tests.yml/badge.svg?branch=main)](https://github.com/ddeutils/ddeutil-workflow/actions/workflows/tests.yml)
 [![python support version](https://img.shields.io/pypi/pyversions/ddeutil-workflow)](https://pypi.org/project/ddeutil-workflow/)
 [![size](https://img.shields.io/github/languages/code-size/ddeutils/ddeutil-workflow)](https://github.com/ddeutils/ddeutil-workflow)
 [![gh license](https://img.shields.io/github/license/ddeutils/ddeutil-workflow)](https://github.com/ddeutils/ddeutil-workflow/blob/main/LICENSE)
 
-
 **Table of Contents**:
 
 - [Installation](#installation)
 - [Getting Started](#getting-started)
-  - [Connection](#connection)
-  - [Dataset](#dataset)
-  - [Schedule](#schedule)
-- [Pipeline Examples](#examples)
-  - [Python & Shell](#python--shell)
-  - [Tasks (EL)](#tasks-extract--load)
-  - [Hooks (T)](#tasks-transform)
+- [Core Features](#core-features)
+  - [On](#on)
+  - [Pipeline](#pipeline)
+- [Usage](#usage)
+  - [Python & Bash](#python--bash)
+  - [Hook (EL)](#hook-extract--load)
+  - [Hook (T)](#hook-transform)
 - [Configuration](#configuration)
+- [Deployment](#deployment)
 
-This **Utility Workflow** objects was created for easy to make a simple metadata
+This **Workflow** objects was created for easy to make a simple metadata
 driven pipeline that able to **ETL, T, EL, or ELT** by `.yaml` file.
 
 I think we should not create the multiple pipeline per use-case if we able to
@@ -70,7 +72,12 @@ pipeline.
 pip install ddeutil-workflow
 ```
 
-This project need `ddeutil-io`, `ddeutil-model` extension namespace packages.
+This project need `ddeutil-io` extension namespace packages. If you want to install
+this package with application add-ons, you should add `app` in installation;
+
+```shell
+pip install ddeutil-workflow[app]
+```
 
 ## Getting Started
 
@@ -87,38 +94,42 @@ will passing parameters and catching the output for re-use it to next step.
 > dynamic registries instead of main features because it have a lot of maintain
 > vendor codes and deps. (I do not have time to handle this features)
 
----
+### On
 
-### Schedule
+The **On** is schedule object.
 
 ```yaml
-schd_for_node:
-  type: schedule.Schedule
+on_every_5_min:
+  type: on.On
   cron: "*/5 * * * *"
 ```
 
 ```python
-from ddeutil.workflow.on import Schedule
+from ddeutil.workflow.on import On
 
-scdl = Schedule.from_loader(name='schd_for_node', externals={})
-assert '*/5 * * * *' == str(scdl.cronjob)
+schedule = On.from_loader(name='on_every_5_min', externals={})
+assert '*/5 * * * *' == str(schedule.cronjob)
 
-cron_iterate = scdl.generate('2022-01-01 00:00:00')
-assert '2022-01-01 00:05:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
-assert '2022-01-01 00:10:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
-assert '2022-01-01 00:15:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
-assert '2022-01-01 00:20:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
-assert '2022-01-01 00:25:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
+cron_iter = schedule.generate('2022-01-01 00:00:00')
+assert '2022-01-01 00:05:00' f"{cron_iter.next:%Y-%m-%d %H:%M:%S}"
+assert '2022-01-01 00:10:00' f"{cron_iter.next:%Y-%m-%d %H:%M:%S}"
+assert '2022-01-01 00:15:00' f"{cron_iter.next:%Y-%m-%d %H:%M:%S}"
+assert '2022-01-01 00:20:00' f"{cron_iter.next:%Y-%m-%d %H:%M:%S}"
 ```
 
----
-
 ### Pipeline
 
+The **Pipeline** object that is the core feature of this project.
+
 ```yaml
 run_py_local:
   type: ddeutil.workflow.pipeline.Pipeline
-  ...
+  on: 'on_every_5_min'
+  params:
+    author-run:
+      type: str
+    run-date:
+      type: datetime
 ```
 
 ```python
@@ -128,27 +139,39 @@ pipe = Pipeline.from_loader(name='run_py_local', externals={})
 pipe.execute(params={'author-run': 'Local Workflow', 'run-date': '2024-01-01'})
 ```
 
-## Examples
+> [!NOTE]
+> The above parameter use short declarative statement. You can pass a parameter
+> type to the key of a parameter name.
+> ```yaml
+> params:
+>   author-run: str
+>   run-date: datetime
+> ```
+>
+> And for the type, you can remove `ddeutil.workflow` prefix because we can find
+> it by looping search from `WORKFLOW_CORE_REGISTRY` value.
+
+## Usage
 
 This is examples that use workflow file for running common Data Engineering
 use-case.
 
-### Python & Shell
+> [!IMPORTANT]
+> I recommend you to use `task` stage for all actions that you want to do with
+> pipeline object.
 
-The state of doing lists that worker should to do. It be collection of the stage.
+### Python & Bash
 
 ```yaml
 run_py_local:
-  type: ddeutil.workflow.pipeline.Pipeline
+  type: pipeline.Pipeline
   params:
-    author-run:
-      type: str
-    run-date:
-      type: datetime
+    author-run: str
+    run-date: datetime
   jobs:
     first-job:
       stages:
-        - name: Printing Information
+        - name: "Printing Information"
           id: define-func
           run: |
             x = '${{ params.author-run }}'
@@ -157,7 +180,7 @@ run_py_local:
             def echo(name: str):
               print(f'Hello {name}')
 
-        - name: Run Sequence and use var from Above
+        - name: "Run Sequence and use var from Above"
           vars:
             x: ${{ params.author-run }}
           run: |
@@ -165,16 +188,16 @@ run_py_local:
             # Change x value
             x: int = 1
 
-        - name: Call Function
+        - name: "Call Function"
           vars:
             echo: ${{ stages.define-func.outputs.echo }}
           run: |
             echo('Caller')
     second-job:
       stages:
-        - name: Echo Shell Script
+        - name: "Echo Bash Script"
           id: shell-echo
-          shell: |
+          bash: |
             echo "Hello World from Shell"
 ```
 
@@ -192,24 +215,20 @@ pipe.execute(params={'author-run': 'Local Workflow', 'run-date': '2024-01-01'})
 > Hello World from Shell
 ```
 
----
-
-### Tasks (Extract & Load)
+### Hook (Extract & Load)
 
 ```yaml
 pipe_el_pg_to_lake:
-  type: ddeutil.workflow.pipeline.Pipeline
+  type: pipeline.Pipeline
   params:
-    run-date:
-      type: datetime
-    author-email:
-      type: str
+    run-date: datetime
+    author-email: str
   jobs:
     extract-load:
       stages:
         - name: "Extract Load from Postgres to Lake"
           id: extract-load
-          task: tasks/postgres-to-delta@polars
+          uses: tasks/postgres-to-delta@polars
           with:
             source:
               conn: conn_postgres_url
@@ -221,15 +240,11 @@ pipe_el_pg_to_lake:
               endpoint: "/${{ params.name }}"
 ```
 
----
-
-### Tasks (Transform)
-
-> I recommend you to use task for all actions that you want to do.
+### Hook (Transform)
 
 ```yaml
-pipe_hook_mssql_proc:
-  type: ddeutil.workflow.pipeline.Pipeline
+pipeline_hook_mssql_proc:
+  type: pipeline.Pipeline
   params:
     run_date: datetime
     sp_name: str
@@ -240,7 +255,7 @@ pipe_hook_mssql_proc:
       stages:
         - name: "Transform Data in MS SQL Server"
           id: transform
-          task: tasks/mssql-proc@odbc
+          uses: tasks/mssql-proc@odbc
           with:
             exec: ${{ params.sp_name }}
             params:
@@ -250,16 +265,30 @@ pipe_hook_mssql_proc:
               target: ${{ params.target_name }}
 ```
 
-> [!NOTE]
-> The above parameter use short declarative statement. You can pass a parameter
-> type to the key of a parameter name.
-
 ## Configuration
 
-```text
+```bash
+export WORKFLOW_ROOT_PATH=.
+export WORKFLOW_CORE_REGISTRY=ddeutil.workflow,tests.utils
+export WORKFLOW_CORE_PATH_CONF=conf
+```
+
+Application config:
 
+```bash
+export WORKFLOW_APP_DB_URL=postgresql+asyncpg://user:pass@localhost:5432/schedule
+export WORKFLOW_APP_INTERVAL=10
 ```
 
-## License
+## Deployment
 
-This project was licensed under the terms of the [MIT license](LICENSE).
+This package able to run as a application service for receive manual trigger
+from the master node via RestAPI.
+
+> [!WARNING]
+> This feature do not start yet because I still research and find the best tool
+> to use it provision an app service, like `starlette`, `fastapi`, `apscheduler`.
+
+```shell
+(venv) $ workflow start -p 7070
+```

{ddeutil_workflow-0.0.5 → ddeutil_workflow-0.0.6}/README.md

@@ -1,25 +1,25 @@
-# Data Utility: _Workflow_
+# Workflow
 
 [![test](https://github.com/ddeutils/ddeutil-workflow/actions/workflows/tests.yml/badge.svg?branch=main)](https://github.com/ddeutils/ddeutil-workflow/actions/workflows/tests.yml)
 [![python support version](https://img.shields.io/pypi/pyversions/ddeutil-workflow)](https://pypi.org/project/ddeutil-workflow/)
 [![size](https://img.shields.io/github/languages/code-size/ddeutils/ddeutil-workflow)](https://github.com/ddeutils/ddeutil-workflow)
 [![gh license](https://img.shields.io/github/license/ddeutils/ddeutil-workflow)](https://github.com/ddeutils/ddeutil-workflow/blob/main/LICENSE)
 
-
 **Table of Contents**:
 
 - [Installation](#installation)
 - [Getting Started](#getting-started)
-  - [Connection](#connection)
-  - [Dataset](#dataset)
-  - [Schedule](#schedule)
-- [Pipeline Examples](#examples)
-  - [Python & Shell](#python--shell)
-  - [Tasks (EL)](#tasks-extract--load)
-  - [Hooks (T)](#tasks-transform)
+- [Core Features](#core-features)
+  - [On](#on)
+  - [Pipeline](#pipeline)
+- [Usage](#usage)
+  - [Python & Bash](#python--bash)
+  - [Hook (EL)](#hook-extract--load)
+  - [Hook (T)](#hook-transform)
 - [Configuration](#configuration)
+- [Deployment](#deployment)
 
-This **Utility Workflow** objects was created for easy to make a simple metadata
+This **Workflow** objects was created for easy to make a simple metadata
 driven pipeline that able to **ETL, T, EL, or ELT** by `.yaml` file.
 
 I think we should not create the multiple pipeline per use-case if we able to
@@ -42,7 +42,12 @@ pipeline.
 pip install ddeutil-workflow
 ```
 
-This project need `ddeutil-io`, `ddeutil-model` extension namespace packages.
+This project need `ddeutil-io` extension namespace packages. If you want to install
+this package with application add-ons, you should add `app` in installation;
+
+```shell
+pip install ddeutil-workflow[app]
+```
 
 ## Getting Started
 
@@ -59,38 +64,42 @@ will passing parameters and catching the output for re-use it to next step.
 > dynamic registries instead of main features because it have a lot of maintain
 > vendor codes and deps. (I do not have time to handle this features)
 
----
+### On
 
-### Schedule
+The **On** is schedule object.
 
 ```yaml
-schd_for_node:
-  type: schedule.Schedule
+on_every_5_min:
+  type: on.On
   cron: "*/5 * * * *"
 ```
 
 ```python
-from ddeutil.workflow.on import Schedule
+from ddeutil.workflow.on import On
 
-scdl = Schedule.from_loader(name='schd_for_node', externals={})
-assert '*/5 * * * *' == str(scdl.cronjob)
+schedule = On.from_loader(name='on_every_5_min', externals={})
+assert '*/5 * * * *' == str(schedule.cronjob)
 
-cron_iterate = scdl.generate('2022-01-01 00:00:00')
-assert '2022-01-01 00:05:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
-assert '2022-01-01 00:10:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
-assert '2022-01-01 00:15:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
-assert '2022-01-01 00:20:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
-assert '2022-01-01 00:25:00' f"{cron_iterate.next:%Y-%m-%d %H:%M:%S}"
+cron_iter = schedule.generate('2022-01-01 00:00:00')
+assert '2022-01-01 00:05:00' f"{cron_iter.next:%Y-%m-%d %H:%M:%S}"
+assert '2022-01-01 00:10:00' f"{cron_iter.next:%Y-%m-%d %H:%M:%S}"
+assert '2022-01-01 00:15:00' f"{cron_iter.next:%Y-%m-%d %H:%M:%S}"
+assert '2022-01-01 00:20:00' f"{cron_iter.next:%Y-%m-%d %H:%M:%S}"
 ```
 
----
-
 ### Pipeline
 
+The **Pipeline** object that is the core feature of this project.
+
 ```yaml
 run_py_local:
   type: ddeutil.workflow.pipeline.Pipeline
-  ...
+  on: 'on_every_5_min'
+  params:
+    author-run:
+      type: str
+    run-date:
+      type: datetime
 ```
 
 ```python
@@ -100,27 +109,39 @@ pipe = Pipeline.from_loader(name='run_py_local', externals={})
 pipe.execute(params={'author-run': 'Local Workflow', 'run-date': '2024-01-01'})
 ```
 
-## Examples
+> [!NOTE]
+> The above parameter use short declarative statement. You can pass a parameter
+> type to the key of a parameter name.
+> ```yaml
+> params:
+>   author-run: str
+>   run-date: datetime
+> ```
+>
+> And for the type, you can remove `ddeutil.workflow` prefix because we can find
+> it by looping search from `WORKFLOW_CORE_REGISTRY` value.
+
+## Usage
 
 This is examples that use workflow file for running common Data Engineering
 use-case.
 
-### Python & Shell
+> [!IMPORTANT]
+> I recommend you to use `task` stage for all actions that you want to do with
+> pipeline object.
 
-The state of doing lists that worker should to do. It be collection of the stage.
+### Python & Bash
 
 ```yaml
 run_py_local:
-  type: ddeutil.workflow.pipeline.Pipeline
+  type: pipeline.Pipeline
   params:
-    author-run:
-      type: str
-    run-date:
-      type: datetime
+    author-run: str
+    run-date: datetime
   jobs:
     first-job:
       stages:
-        - name: Printing Information
+        - name: "Printing Information"
           id: define-func
           run: |
             x = '${{ params.author-run }}'
@@ -129,7 +150,7 @@ run_py_local:
             def echo(name: str):
               print(f'Hello {name}')
 
-        - name: Run Sequence and use var from Above
+        - name: "Run Sequence and use var from Above"
           vars:
             x: ${{ params.author-run }}
           run: |
@@ -137,16 +158,16 @@ run_py_local:
             # Change x value
             x: int = 1
 
-        - name: Call Function
+        - name: "Call Function"
           vars:
             echo: ${{ stages.define-func.outputs.echo }}
           run: |
             echo('Caller')
     second-job:
       stages:
-        - name: Echo Shell Script
+        - name: "Echo Bash Script"
           id: shell-echo
-          shell: |
+          bash: |
             echo "Hello World from Shell"
 ```
 
@@ -164,24 +185,20 @@ pipe.execute(params={'author-run': 'Local Workflow', 'run-date': '2024-01-01'})
 > Hello World from Shell
 ```
 
----
-
-### Tasks (Extract & Load)
+### Hook (Extract & Load)
 
 ```yaml
 pipe_el_pg_to_lake:
-  type: ddeutil.workflow.pipeline.Pipeline
+  type: pipeline.Pipeline
   params:
-    run-date:
-      type: datetime
-    author-email:
-      type: str
+    run-date: datetime
+    author-email: str
   jobs:
     extract-load:
       stages:
         - name: "Extract Load from Postgres to Lake"
           id: extract-load
-          task: tasks/postgres-to-delta@polars
+          uses: tasks/postgres-to-delta@polars
           with:
             source:
               conn: conn_postgres_url
@@ -193,15 +210,11 @@ pipe_el_pg_to_lake:
               endpoint: "/${{ params.name }}"
 ```
 
----
-
-### Tasks (Transform)
-
-> I recommend you to use task for all actions that you want to do.
+### Hook (Transform)
 
 ```yaml
-pipe_hook_mssql_proc:
-  type: ddeutil.workflow.pipeline.Pipeline
+pipeline_hook_mssql_proc:
+  type: pipeline.Pipeline
   params:
     run_date: datetime
     sp_name: str
@@ -212,7 +225,7 @@ pipe_hook_mssql_proc:
       stages:
         - name: "Transform Data in MS SQL Server"
           id: transform
-          task: tasks/mssql-proc@odbc
+          uses: tasks/mssql-proc@odbc
           with:
             exec: ${{ params.sp_name }}
             params:
@@ -222,16 +235,30 @@ pipe_hook_mssql_proc:
               target: ${{ params.target_name }}
 ```
 
-> [!NOTE]
-> The above parameter use short declarative statement. You can pass a parameter
-> type to the key of a parameter name.
-
 ## Configuration
 
-```text
+```bash
+export WORKFLOW_ROOT_PATH=.
+export WORKFLOW_CORE_REGISTRY=ddeutil.workflow,tests.utils
+export WORKFLOW_CORE_PATH_CONF=conf
+```
+
+Application config:
 
+```bash
+export WORKFLOW_APP_DB_URL=postgresql+asyncpg://user:pass@localhost:5432/schedule
+export WORKFLOW_APP_INTERVAL=10
 ```
 
-## License
+## Deployment
 
-This project was licensed under the terms of the [MIT license](LICENSE).
+This package able to run as a application service for receive manual trigger
+from the master node via RestAPI.
+
+> [!WARNING]
+> This feature do not start yet because I still research and find the best tool
+> to use it provision an app service, like `starlette`, `fastapi`, `apscheduler`.
+
+```shell
+(venv) $ workflow start -p 7070
+```

{ddeutil_workflow-0.0.5 → ddeutil_workflow-0.0.6}/pyproject.toml

@@ -28,10 +28,15 @@ dependencies = [
     "fmtutil",
     "ddeutil-io",
     "python-dotenv==1.0.1",
-    "schedule==1.2.2",
 ]
 dynamic = ["version"]
 
+[project.optional-dependencies]
+app = [
+    "fastapi==0.112.0",
+    "apscheduler[sqlalchemy]==3.10.4",
+]
+
 [project.urls]
 Homepage = "https://github.com/ddeutils/ddeutil-workflow/"
 "Source Code" = "https://github.com/ddeutils/ddeutil-workflow/"

ddeutil_workflow-0.0.6/src/ddeutil/workflow/__about__.py

@@ -0,0 +1 @@
+__version__: str = "0.0.6"

{ddeutil_workflow-0.0.5/src/ddeutil/workflow/tasks → ddeutil_workflow-0.0.6/src/ddeutil/workflow}/__init__.py

@@ -3,4 +3,7 @@
 # Licensed under the MIT License. See LICENSE in the project root for
 # license information.
 # ------------------------------------------------------------------------------
-from .dummy import *
+from .exceptions import StageException
+from .on import On
+from .pipeline import Pipeline
+from .stage import Stage

ddeutil_workflow-0.0.5/src/ddeutil/workflow/__regex.py → ddeutil_workflow-0.0.6/src/ddeutil/workflow/__types.py

@@ -1,8 +1,10 @@
-# -------------------------------------------------------------------------
+# ------------------------------------------------------------------------------
 # Copyright (c) 2022 Korawich Anuttra. All rights reserved.
 # Licensed under the MIT License. See LICENSE in the project root for
 # license information.
-# --------------------------------------------------------------------------
+# ------------------------------------------------------------------------------
+from __future__ import annotations
+
 import re
 from re import (
     IGNORECASE,
@@ -11,9 +13,17 @@ from re import (
     VERBOSE,
     Pattern,
 )
+from typing import Any, Union
+
+TupleStr = tuple[str, ...]
+DictData = dict[str, Any]
+DictStr = dict[str, str]
+Matrix = dict[str, Union[list[str], list[int]]]
+MatrixInclude = list[dict[str, Union[str, int]]]
+MatrixExclude = list[dict[str, Union[str, int]]]
 
 
-class RegexConf:
+class Re:
     """Regular expression config."""
 
     # NOTE: Search caller

{ddeutil_workflow-0.0.5 → ddeutil_workflow-0.0.6}/src/ddeutil/workflow/exceptions.py

@@ -9,4 +9,16 @@ Define Errors Object for Node package
 from __future__ import annotations
 
 
-class TaskException(Exception): ...
+class WorkflowException(Exception): ...
+
+
+class UtilException(WorkflowException): ...
+
+
+class StageException(WorkflowException): ...
+
+
+class JobException(WorkflowException): ...
+
+
+class PipelineException(WorkflowException): ...