duckrun 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

duckrun/core.py

@@ -64,36 +64,50 @@ class Duckrun:
     def _attach_lakehouse(self):
         self._create_onelake_secret()
         try:
+            # Use expensive list operation but filter for _delta_log folders only
+            # This avoids parsing JSON content that causes Iceberg metadata issues
+            print(f"Scanning for Delta tables in {self.schema}... (this may take a moment)")
+            
             list_tables_query = f"""
-                SELECT DISTINCT(split_part(file, '_delta_log', 1)) as tables
-                FROM glob ("abfss://{self.workspace}@onelake.dfs.fabric.microsoft.com/{self.lakehouse_name}.Lakehouse/Tables/*/*/_delta_log/*.json")
+                SELECT DISTINCT
+                    regexp_extract(file, 'Tables/{self.schema}/([^/]+)/_delta_log', 1) as table_name
+                FROM glob("abfss://{self.workspace}@onelake.dfs.fabric.microsoft.com/{self.lakehouse_name}.Lakehouse/Tables/{self.schema}/**")
+                WHERE file LIKE '%/_delta_log/%'
+                  AND file NOT LIKE '%/metadata/%'
+                  AND file NOT LIKE '%/iceberg/%'
+                  AND regexp_extract(file, 'Tables/{self.schema}/([^/]+)/_delta_log', 1) IS NOT NULL
             """
+            
             list_tables_df = self.con.sql(list_tables_query).df()
-            list_tables = list_tables_df['tables'].tolist() if not list_tables_df.empty else []
-
-            if not list_tables:
-                print(f"No Delta tables found in {self.lakehouse_name}.Lakehouse/Tables.")
+            
+            if list_tables_df.empty:
+                print(f"No Delta tables found in {self.lakehouse_name}.Lakehouse/Tables/{self.schema}.")
                 return
+            
+            table_names = list_tables_df['table_name'].tolist()
 
-            print(f"Found {len(list_tables)} Delta tables. Attaching as views...")
+            print(f"Found {len(table_names)} Delta tables. Attaching as views...")
 
-            for table_path in list_tables:
-                parts = table_path.strip("/").split("/")
-                if len(parts) >= 2:
-                    potential_schema = parts[-2]
-                    table = parts[-1]
-                    if potential_schema == self.schema:
-                        try:
-                            self.con.sql(f"""
-                                CREATE OR REPLACE VIEW {table}
-                                AS SELECT * FROM delta_scan('{self.table_base_url}{self.schema}/{table}');
-                            """)
-                        except Exception as e:
-                            print(f"Error creating view for table {table}: {e}")
+            for table in table_names:
+                # Skip Iceberg-related folders and empty names
+                if not table or table in ('metadata', 'iceberg'):
+                    continue
+                
+                try:
+                    self.con.sql(f"""
+                        CREATE OR REPLACE VIEW {table}
+                        AS SELECT * FROM delta_scan('{self.table_base_url}{self.schema}/{table}');
+                    """)
+                    print(f"  ✓ Attached: {table}")
+                except Exception as e:
+                    print(f"  ⚠ Skipped {table}: {str(e)[:100]}")
+                    continue
+            
             print("\nAttached tables (views) in DuckDB:")
             self.con.sql("SELECT name FROM (SHOW ALL TABLES) WHERE database='memory'").show()
         except Exception as e:
             print(f"Error attaching lakehouse: {e}")
+            print("Continuing without pre-attached tables.")
 
     def _normalize_table_name(self, name: str) -> str:
         """Extract base table name before first '__'"""

{duckrun-0.1.1.dist-info → duckrun-0.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.1.1
+Version: 0.1.3
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/djouallah/duckrun
@@ -14,10 +14,16 @@ Requires-Dist: deltalake>=0.18.2
 Requires-Dist: requests>=2.28.0
 Dynamic: license-file
 
-# 🦆 Duckrun
+
+<img src="duckrun.png" width="400" alt="Duckrun">
 
 Simple  task runner for Microsoft Fabric Python notebook, powered by DuckDB and Delta_rs.
 
+
+## Known Limitation
+
+Support only Lakehouse with schema, Workspace and lakehouse names should not contains space
+
 ## Installation
 
 ```bash
@@ -50,6 +56,10 @@ pipeline = [
 lakehouse.run(pipeline)
 ```
 
+## Early Exit
+
+In a pipeline run, if a task fails, the pipeline will stop without running the subsequent tasks.
+
 ## How It Works
 
 Duckrun runs two types of tasks:
@@ -117,8 +127,8 @@ Use `__` to create variants of the same table:
 
 ```python
 pipeline = [
-    ('sales__initial', 'overwrite', {}),    # writes to 'sales' table
-    ('sales__incremental', 'append', {}),   # appends to 'sales' table
+    ('sales__initial', 'overwrite'),    # writes to 'sales' table
+    ('sales__incremental', 'append'),   # appends to 'sales' table
 ]
 ```
 
@@ -134,32 +144,7 @@ lakehouse.sql("SELECT * FROM my_table LIMIT 10").show()
 df = lakehouse.sql("SELECT COUNT(*) FROM sales").df()
 ```
 
-## Real-World Example
 
-```python
-import duckrun as dr
-
-lakehouse = dr.connect(
-    workspace="Analytics",
-    lakehouse_name="Sales", 
-    schema="dbo",
-    sql_folder="./etl"
-)
-
-# Daily pipeline
-daily = [
-    ('download_files', (api_url, local_path)),
-    ('staging_orders', 'overwrite', {'run_date': '2024-06-01'}),
-    ('staging_customers', 'overwrite', {'run_date': '2024-06-01'}),
-    ('fact_sales', 'append'),
-    ('dim_customer', 'overwrite')
-]
-
-lakehouse.run(daily)
-
-# Check results
-lakehouse.sql("SELECT COUNT(*) FROM fact_sales").show()
-```
 
 ## Remote SQL Files
 

duckrun-0.1.3.dist-info/RECORD

@@ -0,0 +1,7 @@
+duckrun/__init__.py,sha256=L0jRtD9Ld8Ti4e6GRvPDdHvkQCFAPHM43GSP7ARh6EM,241
+duckrun/core.py,sha256=Ok2IS15NcV6zFuFKFi2GOe1NKREoBQzjwAay-fCNf38,13774
+duckrun-0.1.3.dist-info/licenses/LICENSE,sha256=-DeQQwdbCbkB4507ZF3QbocysB-EIjDtaLexvqRkGZc,1083
+duckrun-0.1.3.dist-info/METADATA,sha256=BYek_gAWR_6QdCAJQAV7QnhoSQsaG0aprlMtAce9Z0k,3805
+duckrun-0.1.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+duckrun-0.1.3.dist-info/top_level.txt,sha256=BknMEwebbUHrVAp3SC92ps8MPhK7XSYsaogTvi_DmEU,8
+duckrun-0.1.3.dist-info/RECORD,,

duckrun-0.1.1.dist-info/RECORD

@@ -1,7 +0,0 @@
-duckrun/__init__.py,sha256=L0jRtD9Ld8Ti4e6GRvPDdHvkQCFAPHM43GSP7ARh6EM,241
-duckrun/core.py,sha256=-Vf2nYwhdsVpTZS9mGBtm8j_HNAcHR7Cj075pida3Yw,13133
-duckrun-0.1.1.dist-info/licenses/LICENSE,sha256=-DeQQwdbCbkB4507ZF3QbocysB-EIjDtaLexvqRkGZc,1083
-duckrun-0.1.1.dist-info/METADATA,sha256=4KZAURlPgjIDGYW_htE4gdHLi6WX-3gpfrCY0r1sFPE,4114
-duckrun-0.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-duckrun-0.1.1.dist-info/top_level.txt,sha256=BknMEwebbUHrVAp3SC92ps8MPhK7XSYsaogTvi_DmEU,8
-duckrun-0.1.1.dist-info/RECORD,,