sibi-flux 2025.12.0__tar.gz → 2026.1.1__tar.gz

{sibi_flux-2025.12.0 → sibi_flux-2026.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: sibi-flux
-Version: 2025.12.0
+Version: 2026.1.1
 Summary: Sibi Toolkit: A collection of tools for Data Analysis/Engineering.
 Author: Luis Valverde
 Author-email: Luis Valverde <lvalverdeb@gmail.com>
@@ -27,6 +27,7 @@ Requires-Dist: httpx>=0.28.1
 Requires-Dist: opentelemetry-api>=1.38.0
 Requires-Dist: opentelemetry-exporter-otlp>=1.38.0
 Requires-Dist: opentelemetry-sdk>=1.38.0
+Requires-Dist: deep-translator>=1.11.4
 Requires-Dist: sibi-flux[distributed,geospatial,mcp] ; extra == 'complete'
 Requires-Dist: distributed>=2025.11.0 ; extra == 'distributed'
 Requires-Dist: osmnx>=2.0.7 ; extra == 'geospatial'

{sibi_flux-2025.12.0 → sibi_flux-2026.1.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sibi-flux"
-version = "2025.12.0"
+version = "2026.1.1"
 description = "Sibi Toolkit: A collection of tools for Data Analysis/Engineering."
 readme = "README.md"
 authors = [
@@ -33,6 +33,7 @@ dependencies = [
     "opentelemetry-api>=1.38.0",
     "opentelemetry-exporter-otlp>=1.38.0",
     "opentelemetry-sdk>=1.38.0",
+    "deep-translator>=1.11.4",
 ]
 
 [project.optional-dependencies]
@@ -97,6 +98,7 @@ filterwarnings = ["ignore::DeprecationWarning"]
 
 
 [tool.poe.tasks]
+publish = { cmd = "uv publish", envfile = ".env" }
 dev = """
 uvicorn solutions.main:app
     --reload
@@ -108,6 +110,17 @@ uvicorn solutions.main:app
 """
 test = { cmd = "pytest tests/"}
 lint = "black src/"
+build = "uv build"
+dc-sync = "python solutions/generators/datacubes/gen_dc.py sync"
+dc-init = "python solutions/generators/datacubes/gen_dc.py init"
+dc-discover = "python solutions/generators/datacubes/gen_dc.py discover"
+dc-scan = "python solutions/generators/datacubes/gen_dc.py scan"
+dc-match = "python solutions/generators/datacubes/gen_dc.py match"
+dc-map = "python solutions/generators/datacubes/gen_dc.py map"
+
+[tool.poe.tasks.release]
+sequence = ["build","publish"]
+envfile = ".env"  # Loads the token for the whole sequence
 
 [tool.commitizen]
 name = "cz_conventional_commits"

{sibi_flux-2025.12.0 → sibi_flux-2026.1.1}/src/sibi_flux/__init__.py

@@ -21,11 +21,12 @@ from sibi_flux.df_validator._df_validator import DfValidator
 
 # Artifacts
 from sibi_flux.artifacts import ParquetArtifact, BaseArtifact as Artifact
-from sibi_flux.readers.parquet import ParquetReader
+from sibi_flux.parquet import ParquetReader
 
 # Utilities (Sub-packages)
 from sibi_flux import dask_cluster
-from sibi_flux.utils import boilerplate, parquet_saver, clickhouse_writer
+from sibi_flux.utils import clickhouse_writer
+from sibi_flux import parquet
 
 
 __all__ = [
@@ -43,7 +44,6 @@ __all__ = [
     "Artifact",
     "ParquetReader",
     "dask_cluster",
-    "boilerplate",
-    "parquet_saver",
+    "parquet",
     "clickhouse_writer",
 ]

{sibi_flux-2025.12.0 → sibi_flux-2026.1.1}/src/sibi_flux/artifacts/parquet_engine/executor.py

@@ -13,7 +13,7 @@ import functools
 from tqdm import tqdm
 import pandas as pd
 from sibi_flux.core import ManagedResource
-from sibi_flux.utils.parquet_saver import ParquetSaver
+from sibi_flux.parquet import ParquetSaver
 
 from sibi_flux.utils import ensure_slash
 from sibi_flux.utils.retry import with_retry

sibi_flux-2026.1.1/src/sibi_flux/config/__init__.py

@@ -0,0 +1,3 @@
+from .manager import ConfigManager
+
+__all__ = ["ConfigManager"]

{sibi_flux-2025.12.0 → sibi_flux-2026.1.1}/src/sibi_flux/dask_cluster/async_core.py

@@ -4,6 +4,7 @@ Async utilities for Dask operations.
 
 from typing import Any, Optional
 import asyncio
+
 try:
     from dask.distributed import Client
 except ImportError:

{sibi_flux-2025.12.0 → sibi_flux-2026.1.1}/src/sibi_flux/dask_cluster/client_manager.py

@@ -23,6 +23,7 @@ import shutil
 
 try:
     from dask.distributed import Client, LocalCluster, get_client
+
     HAS_DISTRIBUTED = True
 except ImportError:
     Client = object
@@ -231,8 +232,10 @@ class DaskClientMixin:
     def _init_dask_client(self, **kwargs) -> None:
         self._init_params = kwargs
         if not HAS_DISTRIBUTED:
-             self.logger.info("Dask Distributed not installed. Skipping cluster initialization.")
-             return
+            self.logger.info(
+                "Dask Distributed not installed. Skipping cluster initialization."
+            )
+            return
 
         if kwargs.get("dask_client"):
             self.dask_client = kwargs["dask_client"]

{sibi_flux-2025.12.0 → sibi_flux-2026.1.1}/src/sibi_flux/dask_cluster/core.py

@@ -14,15 +14,18 @@ from typing import Any, Callable, Dict, List, Optional, TypeVar
 import dask
 import dask.dataframe as dd
 import pandas as pd
+
 try:
     from dask.distributed import Client, Future
     from dask.distributed import wait as dask_wait
 except ImportError:
     Client = object
     Future = object
+
     def dask_wait(*args, **kwargs):
         pass
 
+
 # Project-specific imports
 from .client_manager import get_persistent_client
 from .exceptions import RECOVERABLE_COMMS

{sibi_flux-2025.12.0 → sibi_flux-2026.1.1}/src/sibi_flux/datacube/_data_cube.py

@@ -175,9 +175,10 @@ class Datacube(DfHelper):
             # but we log it for debugging.
             self.logger.debug(f"Schema inference skipped: {e}")
 
-    def _validate(self, df: DataFrameType) -> DataFrameType:
+    def validate_data(self, df: DataFrameType) -> DataFrameType:
         """
         Runs DfValidator if a schema is configured.
+        Overrides BaseDatacube hook.
         """
         schema = self.config.get("validation_schema")
         if not schema:
@@ -203,6 +204,14 @@ class Datacube(DfHelper):
 
         return validator.get_df()
 
+    async def avalidate_data(self, df: DataFrameType) -> DataFrameType:
+        """
+        Asynchronous validation hook.
+        Offloads synchronous validation (CPU bound) to a thread.
+        """
+        import asyncio
+        return await asyncio.to_thread(self.validate_data, df)
+
     def get_ddl(self, table_name: Optional[str] = None) -> str:
         """
         Generates ClickHouse DDL for the current cube.
@@ -230,7 +239,7 @@ class Datacube(DfHelper):
             # 3. Apply Transform Hook
             df = self.fix_data(df, **kwargs)
             # 4. Validate
-            df = self._validate(df)
+            df = self.validate_data(df)
         else:
             self.logger.debug(f"No data loaded by {self.__class__.__name__}")
 
@@ -254,7 +263,7 @@ class Datacube(DfHelper):
             # 3. Apply Async Transform Hook
             df = await self.afix_data(df, **kwargs)
             # 4. Validate (CPU bound)
-            df = await asyncio.to_thread(self._validate, df)
+            df = await self.avalidate_data(df)
         else:
             self.logger.debug(f"No data loaded by {self.__class__.__name__}")