duckrun 0.1.2__tar.gz → 0.1.4__tar.gz

{duckrun-0.1.2 → duckrun-0.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.1.2
+Version: 0.1.4
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/djouallah/duckrun
@@ -35,14 +35,14 @@ pip install duckrun
 ## Quick Start
 
 ```python
-import duckrun as dr
+import duckrun
 
-# Connect to your Fabric lakehouse
-lakehouse = dr.connect(
+# Connect to your Fabric lakehouse (using `con` pattern)
+con = duckrun.connect(
     workspace="my_workspace",
     lakehouse_name="my_lakehouse", 
     schema="dbo",
-    sql_folder="./sql"  # folder containing your .sql and .py files
+    sql_folder="./sql"  # optional: folder containing your .sql and .py files (only needed for pipeline tasks)
 )
 
 # Define your pipeline
@@ -53,9 +53,11 @@ pipeline = [
 ]
 
 # Run it
-lakehouse.run(pipeline)
+con.run(pipeline)
 ```
 
+Note: the `sql/` folder is optional — if all you want to do is explore data with SQL (for example by calling `con.sql(...)`), you don't need to provide a `sql_folder`.
+
 ## Early Exit
 
 In a pipeline run, if a task fails, the pipeline will stop without running the subsequent tasks.
@@ -138,12 +140,14 @@ Both write to the same `sales` table, but use different SQL files.
 
 ```python
 # Run queries
-lakehouse.sql("SELECT * FROM my_table LIMIT 10").show()
+con.sql("SELECT * FROM my_table LIMIT 10").show()
 
 # Get as DataFrame
-df = lakehouse.sql("SELECT COUNT(*) FROM sales").df()
+df = con.sql("SELECT COUNT(*) FROM sales").df()
 ```
 
+Explanation: DuckDB is connected to the lakehouse through `con`, so it is aware of the tables in that lakehouse (including tables created by your pipelines). That means you can query those tables directly with `con.sql(...)` just like any other DuckDB query. If you don't provide a `sql_folder`, you can still use `con.sql(...)` to explore existing tables.
+
 
 
 ## Remote SQL Files
@@ -151,7 +155,7 @@ df = lakehouse.sql("SELECT COUNT(*) FROM sales").df()
 You can load SQL/Python files from a URL:
 
 ```python
-lakehouse = dr.connect(
+con = duckrun.connect(
     workspace="Analytics",
     lakehouse_name="Sales", 
     schema="dbo",

{duckrun-0.1.2 → duckrun-0.1.4}/README.md

@@ -19,14 +19,14 @@ pip install duckrun
 ## Quick Start
 
 ```python
-import duckrun as dr
+import duckrun
 
-# Connect to your Fabric lakehouse
-lakehouse = dr.connect(
+# Connect to your Fabric lakehouse (using `con` pattern)
+con = duckrun.connect(
     workspace="my_workspace",
     lakehouse_name="my_lakehouse", 
     schema="dbo",
-    sql_folder="./sql"  # folder containing your .sql and .py files
+    sql_folder="./sql"  # optional: folder containing your .sql and .py files (only needed for pipeline tasks)
 )
 
 # Define your pipeline
@@ -37,9 +37,11 @@ pipeline = [
 ]
 
 # Run it
-lakehouse.run(pipeline)
+con.run(pipeline)
 ```
 
+Note: the `sql/` folder is optional — if all you want to do is explore data with SQL (for example by calling `con.sql(...)`), you don't need to provide a `sql_folder`.
+
 ## Early Exit
 
 In a pipeline run, if a task fails, the pipeline will stop without running the subsequent tasks.
@@ -122,12 +124,14 @@ Both write to the same `sales` table, but use different SQL files.
 
 ```python
 # Run queries
-lakehouse.sql("SELECT * FROM my_table LIMIT 10").show()
+con.sql("SELECT * FROM my_table LIMIT 10").show()
 
 # Get as DataFrame
-df = lakehouse.sql("SELECT COUNT(*) FROM sales").df()
+df = con.sql("SELECT COUNT(*) FROM sales").df()
 ```
 
+Explanation: DuckDB is connected to the lakehouse through `con`, so it is aware of the tables in that lakehouse (including tables created by your pipelines). That means you can query those tables directly with `con.sql(...)` just like any other DuckDB query. If you don't provide a `sql_folder`, you can still use `con.sql(...)` to explore existing tables.
+
 
 
 ## Remote SQL Files
@@ -135,7 +139,7 @@ df = lakehouse.sql("SELECT COUNT(*) FROM sales").df()
 You can load SQL/Python files from a URL:
 
 ```python
-lakehouse = dr.connect(
+con = duckrun.connect(
     workspace="Analytics",
     lakehouse_name="Sales", 
     schema="dbo",

{duckrun-0.1.2 → duckrun-0.1.4}/duckrun/core.py

@@ -16,23 +16,21 @@ class Duckrun:
         SQL:    ('table_name', 'mode', {params})
     
     Usage:
+        # For pipelines:
         dr = Duckrun.connect(workspace, lakehouse, schema, sql_folder)
-        
-        pipeline = [
-            ('download', (urls, paths, depth)),
-            ('staging', 'overwrite', {'run_date': '2024-06-01'}),
-            ('transform', 'append')
-        ]
-        
         dr.run(pipeline)
+        
+        # For data exploration only:
+        dr = Duckrun.connect(workspace, lakehouse, schema)
+        dr.sql("SELECT * FROM table").show()
     """
 
     def __init__(self, workspace: str, lakehouse_name: str, schema: str, 
-                 sql_folder: str, compaction_threshold: int = 10):
+                 sql_folder: Optional[str] = None, compaction_threshold: int = 10):
         self.workspace = workspace
         self.lakehouse_name = lakehouse_name
         self.schema = schema
-        self.sql_folder = sql_folder.strip()
+        self.sql_folder = sql_folder.strip() if sql_folder else None
         self.compaction_threshold = compaction_threshold
         self.table_base_url = f'abfss://{workspace}@onelake.dfs.fabric.microsoft.com/{lakehouse_name}.Lakehouse/Tables/'
         self.con = duckdb.connect()
@@ -41,7 +39,7 @@ class Duckrun:
 
     @classmethod
     def connect(cls, workspace: str, lakehouse_name: str, schema: str, 
-                sql_folder: str, compaction_threshold: int = 10):
+                sql_folder: Optional[str] = None, compaction_threshold: int = 100):
         """Create and connect to lakehouse"""
         print("Connecting to Lakehouse...")
         return cls(workspace, lakehouse_name, schema, sql_folder, compaction_threshold)
@@ -64,44 +62,44 @@ class Duckrun:
     def _attach_lakehouse(self):
         self._create_onelake_secret()
         try:
-            # Exclude Iceberg metadata folders when scanning for Delta tables
+            # 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")
-                WHERE file NOT LIKE '%/metadata/%'
+                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 split_part(file, '_delta_log', 1) NOT LIKE '%/metadata'
-                  AND split_part(file, '_delta_log', 1) 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]
-                    
-                    # Skip Iceberg-related folders
-                    if table in ('metadata', 'iceberg') or potential_schema in ('metadata', 'iceberg'):
-                        continue
-                        
-                    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}');
-                            """)
-                            print(f"  ✓ Attached: {table}")
-                        except Exception as e:
-                            print(f"  ⚠ Skipped {table}: {str(e)[:100]}")
-                            continue
+            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()
@@ -114,6 +112,9 @@ class Duckrun:
         return name.split('__', 1)[0] if '__' in name else name
 
     def _read_sql_file(self, table_name: str, params: Optional[Dict] = None) -> Optional[str]:
+        if self.sql_folder is None:
+            raise RuntimeError("sql_folder is not configured. Cannot read SQL files.")
+        
         is_url = self.sql_folder.startswith("http")
         if is_url:
             url = f"{self.sql_folder.rstrip('/')}/{table_name}.sql".strip()
@@ -159,6 +160,9 @@ class Duckrun:
         return content
 
     def _load_py_function(self, name: str) -> Optional[Callable]:
+        if self.sql_folder is None:
+            raise RuntimeError("sql_folder is not configured. Cannot load Python functions.")
+        
         is_url = self.sql_folder.startswith("http")
         try:
             if is_url:
@@ -267,6 +271,9 @@ class Duckrun:
             ]
             dr.run(pipeline)
         """
+        if self.sql_folder is None:
+            raise RuntimeError("sql_folder is not configured. Cannot run pipelines. Set sql_folder when creating connection.")
+        
         for i, task in enumerate(pipeline, 1):
             print(f"\n{'='*60}")
             print(f"Task {i}/{len(pipeline)}: {task[0]}")

{duckrun-0.1.2 → duckrun-0.1.4}/duckrun.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.1.2
+Version: 0.1.4
 Summary: Lakehouse task runner powered by DuckDB for Microsoft Fabric
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/djouallah/duckrun
@@ -35,14 +35,14 @@ pip install duckrun
 ## Quick Start
 
 ```python
-import duckrun as dr
+import duckrun
 
-# Connect to your Fabric lakehouse
-lakehouse = dr.connect(
+# Connect to your Fabric lakehouse (using `con` pattern)
+con = duckrun.connect(
     workspace="my_workspace",
     lakehouse_name="my_lakehouse", 
     schema="dbo",
-    sql_folder="./sql"  # folder containing your .sql and .py files
+    sql_folder="./sql"  # optional: folder containing your .sql and .py files (only needed for pipeline tasks)
 )
 
 # Define your pipeline
@@ -53,9 +53,11 @@ pipeline = [
 ]
 
 # Run it
-lakehouse.run(pipeline)
+con.run(pipeline)
 ```
 
+Note: the `sql/` folder is optional — if all you want to do is explore data with SQL (for example by calling `con.sql(...)`), you don't need to provide a `sql_folder`.
+
 ## Early Exit
 
 In a pipeline run, if a task fails, the pipeline will stop without running the subsequent tasks.
@@ -138,12 +140,14 @@ Both write to the same `sales` table, but use different SQL files.
 
 ```python
 # Run queries
-lakehouse.sql("SELECT * FROM my_table LIMIT 10").show()
+con.sql("SELECT * FROM my_table LIMIT 10").show()
 
 # Get as DataFrame
-df = lakehouse.sql("SELECT COUNT(*) FROM sales").df()
+df = con.sql("SELECT COUNT(*) FROM sales").df()
 ```
 
+Explanation: DuckDB is connected to the lakehouse through `con`, so it is aware of the tables in that lakehouse (including tables created by your pipelines). That means you can query those tables directly with `con.sql(...)` just like any other DuckDB query. If you don't provide a `sql_folder`, you can still use `con.sql(...)` to explore existing tables.
+
 
 
 ## Remote SQL Files
@@ -151,7 +155,7 @@ df = lakehouse.sql("SELECT COUNT(*) FROM sales").df()
 You can load SQL/Python files from a URL:
 
 ```python
-lakehouse = dr.connect(
+con = duckrun.connect(
     workspace="Analytics",
     lakehouse_name="Sales", 
     schema="dbo",

{duckrun-0.1.2 → duckrun-0.1.4}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.1.2"
+version = "0.1.4"
 description = "Lakehouse task runner powered by DuckDB for Microsoft Fabric"
 readme = "README.md"
 license = "MIT"