duckrun 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

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)
@@ -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-0.1.3.dist-info → duckrun-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.1.3
+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-0.1.4.dist-info/RECORD

@@ -0,0 +1,7 @@
+duckrun/__init__.py,sha256=L0jRtD9Ld8Ti4e6GRvPDdHvkQCFAPHM43GSP7ARh6EM,241
+duckrun/core.py,sha256=u56bWZDKevbplARgnFdI0wm9BfrIVyAiu3eOIwE5FJc,14259
+duckrun-0.1.4.dist-info/licenses/LICENSE,sha256=-DeQQwdbCbkB4507ZF3QbocysB-EIjDtaLexvqRkGZc,1083
+duckrun-0.1.4.dist-info/METADATA,sha256=eoPhYn2zC0s_YyEGdiCe1Gs7iWfKY9vakYm3rZdMrrs,4377
+duckrun-0.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+duckrun-0.1.4.dist-info/top_level.txt,sha256=BknMEwebbUHrVAp3SC92ps8MPhK7XSYsaogTvi_DmEU,8
+duckrun-0.1.4.dist-info/RECORD,,

duckrun-0.1.3.dist-info/RECORD

@@ -1,7 +0,0 @@
-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,,