duckrun 0.2.19.dev0__tar.gz → 0.2.19.dev1__tar.gz

{duckrun-0.2.19.dev0 → duckrun-0.2.19.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.19.dev0
+Version: 0.2.19.dev1
 Summary: Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)
 Author: mim
 License: MIT

{duckrun-0.2.19.dev0 → duckrun-0.2.19.dev1}/duckrun/stats.py

@@ -290,25 +290,16 @@ def get_stats(duckrun_instance, source: str = None, detailed = False):
             else:
                 # Get parquet metadata and create temp table with compression info
                 if detailed == True:
-                    # Detailed mode: Include row group level statistics
+                    # Detailed mode: Include ALL parquet_metadata columns
                     con.execute(f'''
                         CREATE OR REPLACE TEMP TABLE tbl_{idx} AS
                         SELECT 
                             '{schema_name}' as schema,
                             '{tbl}' as tbl,
-                            pm.file_name,
-                            pm.row_group_id,
-                            pm.row_group_num_rows,
-                            pm.row_group_num_columns,
-                            pm.row_group_bytes,
                             {vorder} as vorder,
-                            pm.compression,
-                            pm.total_compressed_size,
-                            pm.total_uncompressed_size,
-                            ROUND(pm.total_compressed_size::DOUBLE / NULLIF(pm.total_uncompressed_size, 0), 4) as compression_ratio,
+                            pm.*,
                             '{timestamp}' as timestamp
                         FROM parquet_metadata({delta}) pm
-                        WHERE pm.column_id = 0  -- Only include first column to avoid duplication per column
                     ''')
                 else:
                     # Aggregated mode: Original summary statistics
@@ -377,25 +368,16 @@ def get_stats(duckrun_instance, source: str = None, detailed = False):
                     
                     # Use parquet_file_metadata to get actual parquet stats with compression
                     if detailed == True:
-                        # Detailed mode: Include row group level statistics
+                        # Detailed mode: Include ALL parquet_metadata columns
                         con.execute(f'''
                             CREATE OR REPLACE TEMP TABLE tbl_{idx} AS
                             SELECT 
                                 '{schema_name}' as schema,
                                 '{tbl}' as tbl,
-                                pm.file_name,
-                                pm.row_group_id,
-                                pm.row_group_num_rows,
-                                pm.row_group_num_columns,
-                                pm.row_group_bytes,
                                 false as vorder,
-                                pm.compression,
-                                pm.total_compressed_size,
-                                pm.total_uncompressed_size,
-                                ROUND(pm.total_compressed_size::DOUBLE / NULLIF(pm.total_uncompressed_size, 0), 4) as compression_ratio,
+                                pm.*,
                                 '{timestamp}' as timestamp
                             FROM parquet_metadata({filenames}) pm
-                            WHERE pm.column_id = 0  -- Only include first column to avoid duplication per column
                         ''')
                     else:
                         # Aggregated mode: Original summary statistics
@@ -431,9 +413,7 @@ def get_stats(duckrun_instance, source: str = None, detailed = False):
         print("⚠️  No tables could be processed successfully")
         import pandas as pd
         if detailed == True:
-            return pd.DataFrame(columns=['schema', 'tbl', 'file_name', 'row_group_id', 'row_group_num_rows', 
-                                         'row_group_num_columns', 'row_group_bytes', 'vorder', 'compression',
-                                         'total_compressed_size', 'total_uncompressed_size', 'compression_ratio', 'timestamp'])
+            return pd.DataFrame(columns=['schema', 'tbl', 'vorder', 'timestamp'])
         else:
             return pd.DataFrame(columns=['schema', 'tbl', 'total_rows', 'num_files', 'num_row_group', 
                                          'average_row_group', 'file_size_MB', 'vorder', 'compression', 'timestamp'])
@@ -444,25 +424,12 @@ def get_stats(duckrun_instance, source: str = None, detailed = False):
     
     # Generate final summary based on detailed flag
     if detailed == True:
-        # Detailed mode: Return row group level data without aggregation
+        # Detailed mode: Return ALL parquet_metadata columns
         final_result = con.execute(f'''
-            SELECT 
-                schema,
-                tbl,
-                file_name,
-                row_group_id,
-                row_group_num_rows,
-                row_group_num_columns,
-                row_group_bytes,
-                vorder,
-                compression,
-                total_compressed_size,
-                total_uncompressed_size,
-                compression_ratio,
-                timestamp
+            SELECT *
             FROM ({union_query})
             WHERE tbl IS NOT NULL
-            ORDER BY schema, tbl, file_name, row_group_id
+            ORDER BY schema, tbl, file_name, row_group_id, column_id
         ''').df()
     else:
         # Aggregated mode: Original summary statistics

{duckrun-0.2.19.dev0 → duckrun-0.2.19.dev1}/duckrun.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.19.dev0
+Version: 0.2.19.dev1
 Summary: Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)
 Author: mim
 License: MIT

{duckrun-0.2.19.dev0 → duckrun-0.2.19.dev1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.2.19.dev0"
+version = "0.2.19.dev1"
 description = "Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)"
 readme = "README.md"
 license = {text = "MIT"}