ddeutil-workflow 0.0.34__tar.gz → 0.0.35__tar.gz

{ddeutil_workflow-0.0.34/src/ddeutil_workflow.egg-info → ddeutil_workflow-0.0.35}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ddeutil-workflow
-Version: 0.0.34
+Version: 0.0.35
 Summary: Lightweight workflow orchestration
 Author-email: ddeutils <korawich.anu@gmail.com>
 License: MIT
@@ -62,7 +62,7 @@ configuration. It called **Metadata Driven Data Workflow**.
 1. The Minimum frequency unit of scheduling is **1 minute** :warning:
 2. Can not re-run only failed stage and its pending downstream :rotating_light:
 3. All parallel tasks inside workflow engine use Multi-Threading
-   (Python 3.13 unlock GIL :unlock:)
+   (🐍 Python 3.13 unlock GIL :unlock:)
 
 ---
 
@@ -86,37 +86,40 @@ flowchart LR
         B@{ shape: rounded, label: "Workflow<br>Application" }
     end
 
-    A <--->|action &<br>response| B
-    B -....-> |response| G
-    G -....-> |request| B
+    A <-->|action &<br>response| B
+    B -...-> |response| G
+    G -...-> |request| B
 
     subgraph Data Context
-    D@{ shape: processes, label: "Logs" }
-    E@{ shape: lin-cyl, label: "Audit<br>Logs" }
+        D@{ shape: processes, label: "Logs" }
+        E@{ shape: lin-cyl, label: "Audit<br>Logs" }
     end
 
     subgraph Git Context
-    F@{ shape: tag-rect, label: "YAML<br>files" }
+        F@{ shape: tag-rect, label: "YAML<br>files" }
     end
 
-    B --->|disable| F
-    F --->|read| B
+    A ---> |push| H(Repo)
+    H -.-> |pull| F
 
-    B --->|write| E
-    E --->|read| B
-    B --->|write| D
+    B <-->|disable &<br>read| F
+
+    B <-->|read &<br>write| E
+
+    B -->|write| D
 
     D -.->|read| G
     E -.->|read| G
 ```
 
 > [!WARNING]
-> _Disclaimer_: I inspire the dynamic statement from the [**GitHub Action**](https://github.com/features/actions)
-> with `.yml` files and all configs file from several data orchestration framework
-> tools from my experience on Data Engineer. :grimacing:
->
-> Other workflow tools that I interest on them and pick some interested feature
-> implement to this package:
+> _**Disclaimer**_: I inspire the dynamic YAML statement from the [**GitHub Action**](https://github.com/features/actions),
+> and all configs pattern from several data orchestration framework tools from
+> my data engineering experience. :grimacing:
+
+> [!NOTE]
+> Other workflow orchestration tools that I interest and pick them to be inspiration
+> some for this package:
 >
 > - [Google **Workflows**](https://cloud.google.com/workflows)
 > - [AWS **Step Functions**](https://aws.amazon.com/step-functions/)

{ddeutil_workflow-0.0.34 → ddeutil_workflow-0.0.35}/README.md

@@ -30,7 +30,7 @@ configuration. It called **Metadata Driven Data Workflow**.
 1. The Minimum frequency unit of scheduling is **1 minute** :warning:
 2. Can not re-run only failed stage and its pending downstream :rotating_light:
 3. All parallel tasks inside workflow engine use Multi-Threading
-   (Python 3.13 unlock GIL :unlock:)
+   (🐍 Python 3.13 unlock GIL :unlock:)
 
 ---
 
@@ -54,37 +54,40 @@ flowchart LR
         B@{ shape: rounded, label: "Workflow<br>Application" }
     end
 
-    A <--->|action &<br>response| B
-    B -....-> |response| G
-    G -....-> |request| B
+    A <-->|action &<br>response| B
+    B -...-> |response| G
+    G -...-> |request| B
 
     subgraph Data Context
-    D@{ shape: processes, label: "Logs" }
-    E@{ shape: lin-cyl, label: "Audit<br>Logs" }
+        D@{ shape: processes, label: "Logs" }
+        E@{ shape: lin-cyl, label: "Audit<br>Logs" }
     end
 
     subgraph Git Context
-    F@{ shape: tag-rect, label: "YAML<br>files" }
+        F@{ shape: tag-rect, label: "YAML<br>files" }
     end
 
-    B --->|disable| F
-    F --->|read| B
+    A ---> |push| H(Repo)
+    H -.-> |pull| F
 
-    B --->|write| E
-    E --->|read| B
-    B --->|write| D
+    B <-->|disable &<br>read| F
+
+    B <-->|read &<br>write| E
+
+    B -->|write| D
 
     D -.->|read| G
     E -.->|read| G
 ```
 
 > [!WARNING]
-> _Disclaimer_: I inspire the dynamic statement from the [**GitHub Action**](https://github.com/features/actions)
-> with `.yml` files and all configs file from several data orchestration framework
-> tools from my experience on Data Engineer. :grimacing:
->
-> Other workflow tools that I interest on them and pick some interested feature
-> implement to this package:
+> _**Disclaimer**_: I inspire the dynamic YAML statement from the [**GitHub Action**](https://github.com/features/actions),
+> and all configs pattern from several data orchestration framework tools from
+> my data engineering experience. :grimacing:
+
+> [!NOTE]
+> Other workflow orchestration tools that I interest and pick them to be inspiration
+> some for this package:
 >
 > - [Google **Workflows**](https://cloud.google.com/workflows)
 > - [AWS **Step Functions**](https://aws.amazon.com/step-functions/)

ddeutil_workflow-0.0.35/src/ddeutil/workflow/__about__.py

@@ -0,0 +1 @@
+__version__: str = "0.0.35"

{ddeutil_workflow-0.0.34 → ddeutil_workflow-0.0.35}/src/ddeutil/workflow/__init__.py

@@ -9,7 +9,7 @@ from .audit import (
     Audit,
     get_audit,
 )
-from .call import (
+from .caller import (
     ReturnTagFunc,
     TagFunc,
     extract_call,
@@ -39,6 +39,11 @@ from .job import (
     Job,
     Strategy,
 )
+from .logs import (
+    TraceLog,
+    get_dt_tznow,
+    get_trace,
+)
 from .params import (
     ChoiceParam,
     DatetimeParam,
@@ -49,9 +54,7 @@ from .params import (
 from .result import (
     Result,
     Status,
-    TraceLog,
     default_gen_id,
-    get_dt_tznow,
 )
 from .scheduler import (
     Schedule,

{ddeutil_workflow-0.0.34 → ddeutil_workflow-0.0.35}/src/ddeutil/workflow/api/api.py

@@ -20,6 +20,7 @@ from ..conf import config, get_logger
 from ..scheduler import ReleaseThread, ReleaseThreads
 from ..workflow import ReleaseQueue, WorkflowTask
 from .repeat import repeat_at
+from .routes import log
 
 load_dotenv()
 logger = get_logger("ddeutil.workflow")
@@ -77,22 +78,26 @@ async def health():
     return {"message": "Workflow API already start up"}
 
 
-# NOTE: Enable the workflow route.
+# NOTE Add the logs route by default.
+app.include_router(log, prefix=config.prefix_path)
+
+
+# NOTE: Enable the workflows route.
 if config.enable_route_workflow:
-    from .route import workflow_route
+    from .routes import workflow
 
-    app.include_router(workflow_route, prefix=config.prefix_path)
+    app.include_router(workflow, prefix=config.prefix_path)
 
 
-# NOTE: Enable the schedule route.
+# NOTE: Enable the schedules route.
 if config.enable_route_schedule:
     from ..audit import get_audit
     from ..scheduler import schedule_task
-    from .route import schedule_route
+    from .routes import schedule
 
-    app.include_router(schedule_route, prefix=config.prefix_path)
+    app.include_router(schedule, prefix=config.prefix_path)
 
-    @schedule_route.on_event("startup")
+    @schedule.on_event("startup")
     @repeat_at(cron="* * * * *", delay=2)
     def scheduler_listener():
         """Schedule broker every minute at 02 second."""
@@ -109,7 +114,7 @@ if config.enable_route_schedule:
                 log=get_audit(),
             )
 
-    @schedule_route.on_event("startup")
+    @schedule.on_event("startup")
     @repeat_at(cron="*/5 * * * *", delay=10)
     def monitoring():
         logger.debug("[MONITOR]: Start monitoring threading.")

ddeutil_workflow-0.0.35/src/ddeutil/workflow/api/routes/__init__.py

@@ -0,0 +1,8 @@
+# ------------------------------------------------------------------------------
+# Copyright (c) 2022 Korawich Anuttra. All rights reserved.
+# Licensed under the MIT License. See LICENSE in the project root for
+# license information.
+# ------------------------------------------------------------------------------
+from .logs import log_route as log
+from .schedules import schedule_route as schedule
+from .workflows import workflow_route as workflow

ddeutil_workflow-0.0.35/src/ddeutil/workflow/api/routes/logs.py

@@ -0,0 +1,36 @@
+# ------------------------------------------------------------------------------
+# 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
+
+from fastapi import APIRouter
+from fastapi.responses import UJSONResponse
+
+from ...conf import get_logger
+from ...logs import get_trace_obj
+
+logger = get_logger("ddeutil.workflow")
+
+
+# NOTE: Start create the schedule routes.
+#
+log_route = APIRouter(
+    prefix="/logs",
+    tags=["logs"],
+    default_response_class=UJSONResponse,
+)
+
+
+@log_route.get(path="/")
+async def get_logs():
+    return {
+        "message": "Getting logs",
+        "audits": list(get_trace_obj().find_logs()),
+    }
+
+
+@log_route.get(path="/{run_id}")
+async def get_log_with_run_id(run_id: str):
+    return get_trace_obj().find_log_with_id(run_id)

ddeutil_workflow-0.0.34/src/ddeutil/workflow/api/route.py → ddeutil_workflow-0.0.35/src/ddeutil/workflow/api/routes/schedules.py

@@ -6,30 +6,17 @@
 from __future__ import annotations
 
 import copy
-from dataclasses import asdict
 from datetime import datetime, timedelta
-from typing import Any
 
 from fastapi import APIRouter, HTTPException, Request
 from fastapi import status as st
 from fastapi.responses import UJSONResponse
-from pydantic import BaseModel
 
-from ..__types import DictData
-from ..audit import Audit, get_audit
-from ..conf import Loader, config, get_logger
-from ..result import Result
-from ..scheduler import Schedule
-from ..workflow import Workflow
+from ...conf import config, get_logger
+from ...scheduler import Schedule
 
 logger = get_logger("ddeutil.workflow")
 
-workflow_route = APIRouter(
-    prefix="/workflows",
-    tags=["workflows"],
-    default_response_class=UJSONResponse,
-)
-
 schedule_route = APIRouter(
     prefix="/schedules",
     tags=["schedules"],
@@ -37,122 +24,6 @@ schedule_route = APIRouter(
 )
 
 
-@workflow_route.get(path="/")
-async def get_workflows() -> DictData:
-    """Return all workflow workflows that exists in config path."""
-    workflows: DictData = dict(Loader.finds(Workflow))
-    return {
-        "message": f"Getting all workflows: {len(workflows)}",
-        "count": len(workflows),
-        "workflows": workflows,
-    }
-
-
-@workflow_route.get(path="/{name}")
-async def get_workflow_by_name(name: str) -> DictData:
-    """Return model of workflow that passing an input workflow name."""
-    try:
-        workflow: Workflow = Workflow.from_loader(name=name, externals={})
-    except ValueError as err:
-        logger.exception(err)
-        raise HTTPException(
-            status_code=st.HTTP_404_NOT_FOUND,
-            detail=(
-                f"Workflow workflow name: {name!r} does not found in /conf path"
-            ),
-        ) from None
-    return workflow.model_dump(
-        by_alias=True,
-        exclude_none=True,
-        exclude_unset=True,
-        exclude_defaults=True,
-    )
-
-
-class ExecutePayload(BaseModel):
-    params: dict[str, Any]
-
-
-@workflow_route.post(path="/{name}/execute", status_code=st.HTTP_202_ACCEPTED)
-async def execute_workflow(name: str, payload: ExecutePayload) -> DictData:
-    """Return model of workflow that passing an input workflow name."""
-    try:
-        workflow: Workflow = Workflow.from_loader(name=name, externals={})
-    except ValueError:
-        raise HTTPException(
-            status_code=st.HTTP_404_NOT_FOUND,
-            detail=(
-                f"Workflow workflow name: {name!r} does not found in /conf path"
-            ),
-        ) from None
-
-    # NOTE: Start execute manually
-    try:
-        result: Result = workflow.execute(params=payload.params)
-    except Exception as err:
-        raise HTTPException(
-            status_code=st.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=f"{type(err)}: {err}",
-        ) from None
-
-    return asdict(result)
-
-
-@workflow_route.get(path="/{name}/logs")
-async def get_workflow_logs(name: str):
-    try:
-        return {
-            "message": f"Getting workflow {name!r} logs",
-            "logs": [
-                log.model_dump(
-                    by_alias=True,
-                    exclude_none=True,
-                    exclude_unset=True,
-                    exclude_defaults=True,
-                )
-                for log in get_audit().find_audits(name=name)
-            ],
-        }
-    except FileNotFoundError:
-        raise HTTPException(
-            status_code=st.HTTP_404_NOT_FOUND,
-            detail=f"Does not found log for workflow {name!r}",
-        ) from None
-
-
-@workflow_route.get(path="/{name}/logs/{release}")
-async def get_workflow_release_log(name: str, release: str):
-    try:
-        log: Audit = get_audit().find_audit_with_release(
-            name=name, release=datetime.strptime(release, "%Y%m%d%H%M%S")
-        )
-    except FileNotFoundError:
-        raise HTTPException(
-            status_code=st.HTTP_404_NOT_FOUND,
-            detail=(
-                f"Does not found log for workflow {name!r} "
-                f"with release {release!r}"
-            ),
-        ) from None
-    return {
-        "message": f"Getting workflow {name!r} log in release {release}",
-        "log": log.model_dump(
-            by_alias=True,
-            exclude_none=True,
-            exclude_unset=True,
-            exclude_defaults=True,
-        ),
-    }
-
-
-@workflow_route.delete(
-    path="/{name}/logs/{release}",
-    status_code=st.HTTP_204_NO_CONTENT,
-)
-async def del_workflow_release_log(name: str, release: str):
-    return {"message": f"Deleted workflow {name!r} log in release {release}"}
-
-
 @schedule_route.get(path="/{name}")
 async def get_schedules(name: str):
     try:

ddeutil_workflow-0.0.35/src/ddeutil/workflow/api/routes/workflows.py

@@ -0,0 +1,137 @@
+# ------------------------------------------------------------------------------
+# 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
+
+from dataclasses import asdict
+from datetime import datetime
+from typing import Any
+
+from fastapi import APIRouter, HTTPException
+from fastapi import status as st
+from fastapi.responses import UJSONResponse
+from pydantic import BaseModel
+
+from ...__types import DictData
+from ...audit import Audit, get_audit
+from ...conf import Loader, get_logger
+from ...result import Result
+from ...workflow import Workflow
+
+logger = get_logger("ddeutil.workflow")
+
+workflow_route = APIRouter(
+    prefix="/workflows",
+    tags=["workflows"],
+    default_response_class=UJSONResponse,
+)
+
+
+@workflow_route.get(path="/")
+async def get_workflows() -> DictData:
+    """Return all workflow workflows that exists in config path."""
+    workflows: DictData = dict(Loader.finds(Workflow))
+    return {
+        "message": f"Getting all workflows: {len(workflows)}",
+        "count": len(workflows),
+        "workflows": workflows,
+    }
+
+
+@workflow_route.get(path="/{name}")
+async def get_workflow_by_name(name: str) -> DictData:
+    """Return model of workflow that passing an input workflow name."""
+    try:
+        workflow: Workflow = Workflow.from_loader(name=name, externals={})
+    except ValueError as err:
+        logger.exception(err)
+        raise HTTPException(
+            status_code=st.HTTP_404_NOT_FOUND,
+            detail=(
+                f"Workflow workflow name: {name!r} does not found in /conf path"
+            ),
+        ) from None
+    return workflow.model_dump(
+        by_alias=True,
+        exclude_none=True,
+        exclude_unset=True,
+        exclude_defaults=True,
+    )
+
+
+class ExecutePayload(BaseModel):
+    params: dict[str, Any]
+
+
+@workflow_route.post(path="/{name}/execute", status_code=st.HTTP_202_ACCEPTED)
+async def execute_workflow(name: str, payload: ExecutePayload) -> DictData:
+    """Return model of workflow that passing an input workflow name."""
+    try:
+        workflow: Workflow = Workflow.from_loader(name=name, externals={})
+    except ValueError:
+        raise HTTPException(
+            status_code=st.HTTP_404_NOT_FOUND,
+            detail=(
+                f"Workflow workflow name: {name!r} does not found in /conf path"
+            ),
+        ) from None
+
+    # NOTE: Start execute manually
+    try:
+        result: Result = workflow.execute(params=payload.params)
+    except Exception as err:
+        raise HTTPException(
+            status_code=st.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"{type(err)}: {err}",
+        ) from None
+
+    return asdict(result)
+
+
+@workflow_route.get(path="/{name}/audits")
+async def get_workflow_audits(name: str):
+    try:
+        return {
+            "message": f"Getting workflow {name!r} audits",
+            "audits": [
+                audit.model_dump(
+                    by_alias=True,
+                    exclude_none=True,
+                    exclude_unset=True,
+                    exclude_defaults=True,
+                )
+                for audit in get_audit().find_audits(name=name)
+            ],
+        }
+    except FileNotFoundError:
+        raise HTTPException(
+            status_code=st.HTTP_404_NOT_FOUND,
+            detail=f"Does not found audit for workflow {name!r}",
+        ) from None
+
+
+@workflow_route.get(path="/{name}/audits/{release}")
+async def get_workflow_release_audit(name: str, release: str):
+    try:
+        audit: Audit = get_audit().find_audit_with_release(
+            name=name, release=datetime.strptime(release, "%Y%m%d%H%M%S")
+        )
+    except FileNotFoundError:
+        raise HTTPException(
+            status_code=st.HTTP_404_NOT_FOUND,
+            detail=(
+                f"Does not found audit for workflow {name!r} "
+                f"with release {release!r}"
+            ),
+        ) from None
+    return {
+        "message": f"Getting workflow {name!r} audit in release {release}",
+        "audit": audit.model_dump(
+            by_alias=True,
+            exclude_none=True,
+            exclude_unset=True,
+            exclude_defaults=True,
+        ),
+    }

{ddeutil_workflow-0.0.34 → ddeutil_workflow-0.0.35}/src/ddeutil/workflow/audit.py

@@ -20,7 +20,7 @@ from typing_extensions import Self
 
 from .__types import DictData, TupleStr
 from .conf import config
-from .result import TraceLog
+from .logs import TraceLog, get_trace
 
 __all__: TupleStr = (
     "get_audit",
@@ -174,7 +174,7 @@ class FileAudit(BaseAudit):
 
         :rtype: Self
         """
-        trace: TraceLog = TraceLog(self.run_id, self.parent_run_id)
+        trace: TraceLog = get_trace(self.run_id, self.parent_run_id)
 
         # NOTE: Check environ variable was set for real writing.
         if not config.enable_write_audit:
@@ -214,7 +214,7 @@ class SQLiteAudit(BaseAudit):  # pragma: no cov
         """Save logging data that receive a context data from a workflow
         execution result.
         """
-        trace: TraceLog = TraceLog(self.run_id, self.parent_run_id)
+        trace: TraceLog = get_trace(self.run_id, self.parent_run_id)
 
         # NOTE: Check environ variable was set for real writing.
         if not config.enable_write_audit:

ddeutil_workflow-0.0.34/src/ddeutil/workflow/call.py → ddeutil_workflow-0.0.35/src/ddeutil/workflow/caller.py

@@ -60,7 +60,7 @@ def tag(
 
         @wraps(func)
         def wrapped(*args: P.args, **kwargs: P.kwargs) -> TagFunc:
-            # NOTE: Able to do anything before calling call function.
+            # NOTE: Able to do anything before calling the call function.
             return func(*args, **kwargs)
 
         return wrapped
@@ -150,7 +150,7 @@ def extract_call(call: str) -> Callable[[], TagFunc]:
     """
     if not (found := Re.RE_TASK_FMT.search(call)):
         raise ValueError(
-            f"Call {call!r} does not match with call format regex."
+            f"Call {call!r} does not match with the call regex format."
         )
 
     # NOTE: Pass the searching call string to `path`, `func`, and `tag`.
@@ -160,13 +160,13 @@ def extract_call(call: str) -> Callable[[], TagFunc]:
     rgt: dict[str, Registry] = make_registry(f"{call.path}")
     if call.func not in rgt:
         raise NotImplementedError(
-            f"``REGISTER-MODULES.{call.path}.registries`` does not "
+            f"`REGISTER-MODULES.{call.path}.registries` does not "
             f"implement registry: {call.func!r}."
         )
 
     if call.tag not in rgt[call.func]:
         raise NotImplementedError(
             f"tag: {call.tag!r} does not found on registry func: "
-            f"``REGISTER-MODULES.{call.path}.registries.{call.func}``"
+            f"`REGISTER-MODULES.{call.path}.registries.{call.func}`"
         )
     return rgt[call.func][call.tag]