easy-data-loader 0.2.1__tar.gz → 0.2.2__tar.gz

{easy_data_loader-0.2.1/src/easy_data_loader.egg-info → easy_data_loader-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: easy_data_loader
-Version: 0.2.1
+Version: 0.2.2
 Summary: Data transfer utilities between files and databases
 Author-email: Bojoi Gabriel <bojoigabriel@gmail.com>
 Classifier: Development Status :: 3 - Alpha
@@ -36,6 +36,8 @@ Dynamic: license-file
 
 **Easy Data Loader** is a flexible, modular Python library designed to streamline ETL (Extract, Transform, Load) processes between various file data sources (csv, xlsx, parquet, orc) and databases (MSSQL, PostgreSQL and others).
 
+The [documentation guide](docs/README.md) is the canonical onboarding path. It is also the source for the self-paced presentation outline in [docs/presentation-outline.md](docs/presentation-outline.md).
+
 ## ✨ Key Features
 - **Declarative Configuration**: Manage connections and pipelines through simple python files and `.env` resources.
 - **Integrated CLI**: Initialize a standardized project structure with a single command.

{easy_data_loader-0.2.1 → easy_data_loader-0.2.2}/README.md

@@ -7,6 +7,8 @@
 
 **Easy Data Loader** is a flexible, modular Python library designed to streamline ETL (Extract, Transform, Load) processes between various file data sources (csv, xlsx, parquet, orc) and databases (MSSQL, PostgreSQL and others).
 
+The [documentation guide](docs/README.md) is the canonical onboarding path. It is also the source for the self-paced presentation outline in [docs/presentation-outline.md](docs/presentation-outline.md).
+
 ## ✨ Key Features
 - **Declarative Configuration**: Manage connections and pipelines through simple python files and `.env` resources.
 - **Integrated CLI**: Initialize a standardized project structure with a single command.

{easy_data_loader-0.2.1 → easy_data_loader-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "easy_data_loader"
-version = "0.2.1"
+version = "0.2.2"
 description = "Data transfer utilities between files and databases"
 authors = [{ name = "Bojoi Gabriel", email = "bojoigabriel@gmail.com" }]
 readme = "README.md"
@@ -30,7 +30,14 @@ classifiers = [
 ]
 
 [dependency-groups]
-dev = ["ipykernel>=7.1.0", "pytest>=8.4.2", "ruff", "mypy", "pre-commit"]
+dev = [
+    "ipykernel>=7.1.0",
+    "mypy",
+    "pre-commit",
+    "pytest>=8.4.2",
+    "python-pptx>=1.0.2",
+    "ruff",
+]
 
 [project.scripts]
 easy-data-loader = "easy_data_loader.cli:main"
@@ -38,6 +45,9 @@ easy-data-loader = "easy_data_loader.cli:main"
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools.package-data]
+"*" = ["*"]
+
 [tool.pytest.ini_options]
 pythonpath = "src"
 

{easy_data_loader-0.2.1 → easy_data_loader-0.2.2}/src/easy_data_loader/cli.py

@@ -6,6 +6,7 @@ from .utils import to_snake_case
 # Integrated templates
 PIPELINE_TEMPLATE = """from easy_data_loader.models import BasePipelineDefinition, ColumnDefinition
 import pandas as pd
+from sqlalchemy import DateTime, Integer, Numeric, String
 
 
 example_pipeline = BasePipelineDefinition(
@@ -28,13 +29,13 @@ example_pipeline = BasePipelineDefinition(
 
     # columns definition if we are sending data to a database table
     columns={
-        "transaction_id": ColumnDefinition(target_name="new_transaction_id", data_type=INT()),
-        "date": ColumnDefinition(target_name="sales_date", data_type=DATETIME()),
-        "customer_id": ColumnDefinition(target_name="id_customer", data_type=INT()),
-        "product_category" : ColumnDefinition(target_name="category_of_product", data_type=NVARCHAR(100)),
-        "units_sold" : ColumnDefinition(target_name="units", data_type=INT()),
-        "unit_price" : ColumnDefinition(target_name="price", data_type=DECIMAL(6,2)),
-        "raw_notes" : ColumnDefinition(target_name="notes", data_type=NVARCHAR(100))
+        "transaction_id": ColumnDefinition(target_name="new_transaction_id", data_type=Integer()),
+        "date": ColumnDefinition(target_name="sales_date", data_type=DateTime()),
+        "customer_id": ColumnDefinition(target_name="id_customer", data_type=Integer()),
+        "product_category" : ColumnDefinition(target_name="category_of_product", data_type=String(100)),
+        "units_sold" : ColumnDefinition(target_name="units", data_type=Integer()),
+        "unit_price" : ColumnDefinition(target_name="price", data_type=Numeric(6,2)),
+        "raw_notes" : ColumnDefinition(target_name="notes", data_type=String(100))
     },
 
     # different parameters passed to the write functions to be forwarded to the pandas function that will write to destination (e.g. to_sql, to_csv, to_excel, etc.)
@@ -118,14 +119,14 @@ MAIN = """from easy_data_loader import LoadPipeline, OrchestratorPipeline, Proce
 
 def main():
     # Run an ETL pipeline
-    first_step = LoadPipeline(pipeline_name="example_pipeline").run()
+    first_step = LoadPipeline(file_name="example_pipeline").run()
 
     # Run a procedure pipeline
     if first_step:
-        ProcedurePipeline(pipeline_name="example_procedure").run()
+        ProcedurePipeline(file_name="example_procedure").run()
 
     # Run an orchestrator pipeline
-    OrchestratorPipeline(pipeline_name="example_orchestrator").run()
+    OrchestratorPipeline(file_name="example_orchestrator").run()
 
 if __name__ == "__main__":
     main()

{easy_data_loader-0.2.1 → easy_data_loader-0.2.2}/src/easy_data_loader/data_inferrence.py

@@ -100,7 +100,7 @@ class SQLAlchemyDTypeInferrer(LoggedComponent):
                 )
                 return {}
 
-            self.logger.info(f"Dtype inference completed for {len(dtype_dict)} columns")
+            self.logger.info(f"Type inference completed for {len(dtype_dict)} columns")
 
             # Only visible in the file log, since it's logged at debug level
             self._log_inference_summary(dtype_dict)
@@ -110,7 +110,7 @@ class SQLAlchemyDTypeInferrer(LoggedComponent):
         except Exception as e:
             # Catch-all for any unexpected errors
             self.logger.error(
-                f"Dtype inference failed completely: {str(e)}. "
+                f"Type inference failed completely: {str(e)}. "
                 f"Returning empty dict - will use default inference.",
                 exc_info=True,
             )

{easy_data_loader-0.2.1 → easy_data_loader-0.2.2}/src/easy_data_loader/log.py

@@ -27,7 +27,8 @@ class AppLogger:
         )
 
         console_formatter = logging.Formatter(
-            "[%(asctime)s]-[%(levelname)s] %(message)s"
+            "[%(asctime)s]-[%(levelname)s] %(message)s",
+            datefmt="%Y-%m-%d %H:%M:%S",
         )
 
         root_logger = logging.getLogger()

{easy_data_loader-0.2.1 → easy_data_loader-0.2.2}/src/easy_data_loader/pipeline.py

@@ -142,15 +142,17 @@ class LoadPipeline(BasePipeline):
         except PipelineValidationError as e:
             self.error_details = str(e)
             self.logger.error(
-                f"Critical pipeline error - {self.definition.pipeline_name}: {str(e)}"
+                f"Critical pipeline error - {self.definition.pipeline_name}"
             )
+            self.logger.debug(str(e))
             self._log_audit("FAILED")
             raise
         except Exception as e:
             self.error_details = str(e)
-            self.log_exception(
-                e, f"Critical pipeline error - {self.definition.pipeline_name}"
+            self.logger.error(
+                f"Critical pipeline error - {self.definition.pipeline_name}"
             )
+            self.logger.debug(str(e))
             self._log_audit("FAILED")
             raise
         finally:
@@ -218,8 +220,10 @@ class LoadPipeline(BasePipeline):
 
             self.logger.error("No valid source configured for the Pipeline")
 
-        except Exception as e:
-            self.log_exception(e, "Extraction step failed")
+        except Exception:
+            self.error_details = "Extraction step failed"
+            self.logger.error(self.error_details)
+            self._log_audit("FAILED")
             raise
 
         return pd.DataFrame(), {}

{easy_data_loader-0.2.1 → easy_data_loader-0.2.2/src/easy_data_loader.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: easy_data_loader
-Version: 0.2.1
+Version: 0.2.2
 Summary: Data transfer utilities between files and databases
 Author-email: Bojoi Gabriel <bojoigabriel@gmail.com>
 Classifier: Development Status :: 3 - Alpha
@@ -36,6 +36,8 @@ Dynamic: license-file
 
 **Easy Data Loader** is a flexible, modular Python library designed to streamline ETL (Extract, Transform, Load) processes between various file data sources (csv, xlsx, parquet, orc) and databases (MSSQL, PostgreSQL and others).
 
+The [documentation guide](docs/README.md) is the canonical onboarding path. It is also the source for the self-paced presentation outline in [docs/presentation-outline.md](docs/presentation-outline.md).
+
 ## ✨ Key Features
 - **Declarative Configuration**: Manage connections and pipelines through simple python files and `.env` resources.
 - **Integrated CLI**: Initialize a standardized project structure with a single command.