dlt-utils 0.7.2__tar.gz → 0.7.3__tar.gz

{dlt_utils-0.7.2 → dlt_utils-0.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dlt_utils
-Version: 0.7.2
+Version: 0.7.3
 Summary: Shared utilities for dlt data pipelines with multi-company support
 Author: Jay van den Bos
 License: MIT

{dlt_utils-0.7.2 → dlt_utils-0.7.3}/dlt_utils/__init__.py

@@ -45,7 +45,7 @@ from .pipeline import (
 )
 
 
-__version__ = "0.7.2"
+__version__ = "0.7.3"
 
 __all__ = [
     # Incremental

{dlt_utils-0.7.2 → dlt_utils-0.7.3}/dlt_utils/pipeline.py

@@ -23,14 +23,14 @@ def validate_refresh_args(
 ) -> None:
     """
     Validate that refresh arguments are used correctly.
-    
+
     Raises ValueError if drop_sources is used with a resource filter,
     as this would drop ALL tables but only reload selected resources.
-    
+
     Args:
         refresh: The refresh mode ('drop_sources' or 'drop_resources').
         resources_filter: List of resources being loaded (None = all).
-        
+
     Raises:
         ValueError: If drop_sources is used with a resource filter.
     """
@@ -49,46 +49,47 @@ def filter_resources(
 ) -> list[str]:
     """
     Filter available resources based on requested resources.
-    
+
     Args:
         available_resources: List of all available resource names.
         requested_resources: List of requested resources (None = all).
-        
+
     Returns:
         List of valid resources to load.
-        
+
     Raises:
         ValueError: If no valid resources are found.
     """
     if requested_resources is None:
         return available_resources
-    
-    valid_resources = [r for r in requested_resources if r in available_resources]
-    
+
+    valid_resources = [
+        r for r in requested_resources if r in available_resources]
+
     if not valid_resources:
         raise ValueError(
             f"No valid resources found. "
             f"Requested: {requested_resources}. "
             f"Available: {available_resources}"
         )
-    
+
     # Log any requested resources that weren't found
     invalid = set(requested_resources) - set(valid_resources)
     if invalid:
         logger.warning(f"Ignored invalid resources: {invalid}")
-    
+
     return valid_resources
 
 
 def print_resources(source: Any) -> None:
     """
     Print available resources from a dlt source and exit.
-    
+
     Args:
         source: A dlt source object with a resources attribute.
     """
     available_resources = sorted(get_resource_names(source))
-    
+
     print("\nAvailable resources:")
     print("-" * 40)
     for resource in available_resources:
@@ -100,10 +101,10 @@ def print_resources(source: Any) -> None:
 def get_resource_names(source: Any) -> list[str]:
     """
     Get list of resource names from a dlt source.
-    
+
     Args:
         source: A dlt source object with a resources attribute.
-        
+
     Returns:
         List of resource names.
     """
@@ -113,20 +114,20 @@ def get_resource_names(source: Any) -> list[str]:
 def mask_sensitive_value(value: str | None, show_chars: int = 2) -> str:
     """
     Mask a sensitive value (like API key) showing only first and middle characters.
-    
+
     Args:
         value: The value to mask.
         show_chars: Number of characters to show at start and middle.
-        
+
     Returns:
         Masked value like "ab..cd..***" or "N/A" if not set.
     """
     if not value:
         return "N/A"
-    
+
     if len(value) < 6:
         return value[:1] + "***"
-    
+
     mid = len(value) // 2
     return f"{value[:show_chars]}..{value[mid:mid+show_chars]}..***"
 
@@ -138,34 +139,34 @@ def cleanup_tombstones(
 ) -> None:
     """
     Clean up tombstone records from tables after a successful pipeline run.
-    
+
     Tombstones are placeholder records used to ensure delete-insert semantics
     work correctly for partitions that have no real data. After the pipeline
     completes, these tombstone records should be removed.
-    
+
     Args:
         pipeline: A dlt pipeline object with sql_client() method.
         resources: List of resource/table names to clean tombstones from.
         column_name: The boolean column name that marks tombstone records.
                      Defaults to "_tt_is_tombstone".
-    
+
     Example:
         # Clean up tombstones from all resources except 'customer'
         tombstone_resources = [r for r in sync_resources if r != "customer"]
         cleanup_tombstones(pipeline, tombstone_resources)
-        
+
         # Clean up with a custom column name
         cleanup_tombstones(pipeline, ["my_table"], column_name="is_tombstone")
     """
     if not resources:
         logger.debug("No resources provided for tombstone cleanup")
         return
-    
+
     with pipeline.sql_client() as sql_client:
         for resource_name in resources:
             table_name = sql_client.make_qualified_table_name(resource_name)
             delete_query = f"DELETE FROM {table_name} WHERE {column_name} = 1"
-            
+
             try:
                 sql_client.execute_sql(delete_query)
                 logger.info(f"Cleaned up tombstone records from {table_name}")
@@ -267,11 +268,12 @@ def print_configs(
         configs: Sequence of dataclass instances to print.
         title: Title for the table header.
         columns: List of (field_name, header_label, width) tuples defining which
-                 fields to display and how. If None, all fields are shown with
-                 auto-generated headers.
-        sensitive_fields: List of field names that contain sensitive data to mask.
+            fields to display and how. If None, all fields are shown with
+            auto-generated headers.
+        sensitive_fields: List of field names that contain sensitive data to mask. Uses
+            auto-detection for dataclass fields with repr=False if not provided.
         mask_func: Function to mask sensitive values. If None, uses mask_sensitive_value
-                   which shows first and middle characters.
+            which shows first and middle characters.
 
     Example:
         print_configs(
@@ -302,8 +304,17 @@ def print_configs(
                 "columns must be provided for non-dataclass configs"
             )
 
-    sensitive_fields = sensitive_fields or []
-    
+    auto_sensitive_fields: set[str] = set()
+    if is_dataclass(configs[0]):
+        auto_sensitive_fields = {
+            f.name for f in fields(configs[0]) if not f.repr
+        }
+
+    if sensitive_fields is None:
+        sensitive_fields = list(auto_sensitive_fields)
+    else:
+        sensitive_fields = list(set(sensitive_fields) | auto_sensitive_fields)
+
     # Use mask_sensitive_value as default mask function
     if mask_func is None:
         mask_func = mask_sensitive_value
@@ -315,11 +326,11 @@ def print_configs(
     # Print header
     print(f"\n{title}:")
     print("-" * total_width)
-    
+
     header = f"{'Index':<{index_width}}"
     header += "".join(f"{label:<{width}}" for _, label, width in columns)
     print(header)
-    
+
     print("-" * total_width)
 
     # Print rows
@@ -327,12 +338,12 @@ def print_configs(
         row = f"{i:<{index_width}}"
         for field_name, _, width in columns:
             value = getattr(config, field_name, None)
-            
+
             if field_name in sensitive_fields:
                 display_value = mask_func(value)
             else:
                 display_value = str(value) if value is not None else "N/A"
-            
+
             row += f"{display_value:<{width}}"
         print(row)
 

{dlt_utils-0.7.2 → dlt_utils-0.7.3}/dlt_utils.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dlt_utils
-Version: 0.7.2
+Version: 0.7.3
 Summary: Shared utilities for dlt data pipelines with multi-company support
 Author: Jay van den Bos
 License: MIT

{dlt_utils-0.7.2 → dlt_utils-0.7.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dlt_utils"
-version = "0.7.2"
+version = "0.7.3"
 description = "Shared utilities for dlt data pipelines with multi-company support"
 readme = "README.md"
 license = { text = "MIT" }