Merge pull request #223 from posit-dev/fix-consistent-input-ingestion

fix: have consistent input ingestion for all classes/functions with a `data=` parameter

Author: rich-iannone

pointblank/assistant.py

@@ -59,8 +59,9 @@ def assistant(
         `"ollama"`, and `"bedrock"`.
     data
         An optional data table to focus on during discussion with the PbA, which could be a
-        DataFrame object or an Ibis table object. Read the *Supported Input Table Types* section for
-        details on the supported table types.
+        DataFrame object, an Ibis table object, a CSV file path, a Parquet file path, or a database
+        connection string. Read the *Supported Input Table Types* section for details on the
+        supported table types.
     tbl_name : str, optional
         The name of the data table. This is optional and is only used to provide a more detailed
         prompt to the PbA.
@@ -142,9 +143,13 @@ def assistant(
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
     - Parquet table (`"parquet"`)*
+    - CSV files (string path or `pathlib.Path` object with `.csv` extension)
+    - Parquet files (string path, `pathlib.Path` object, glob pattern, directory with `.parquet`
+    extension, or partitioned dataset)
+    - Database connection strings (URI format with optional table specification)
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
-    `ibis.expr.types.relations.Table`). Furthermore, using `preview()` with these types of tables
+    `ibis.expr.types.relations.Table`). Furthermore, using `assistant()` with these types of tables
     requires the Ibis library (`v9.5.0` or above) to be installed. If the input table is a Polars or
     Pandas DataFrame, the availability of Ibis is not needed.
     """
@@ -174,6 +179,23 @@ def assistant(
 
     # If a dataset is provided, generate a table summary in JSON format
     if data is not None:
+        # Import processing functions from validate module
+        from pointblank.validate import (
+            _process_connection_string,
+            _process_csv_input,
+            _process_parquet_input,
+        )
+
+        # Process input data to handle different data source types
+        # Handle connection string input (e.g., "duckdb:///path/to/file.ddb::table_name")
+        data = _process_connection_string(data)
+
+        # Handle CSV file input (e.g., "data.csv" or Path("data.csv"))
+        data = _process_csv_input(data)
+
+        # Handle Parquet file input (e.g., "data.parquet", "data/*.parquet", "data/")
+        data = _process_parquet_input(data)
+
         scan = DataScan(data=data)
 
         tbl_type: str = scan.profile.implementation.name.lower()

pointblank/compare.py

@@ -10,6 +10,23 @@
 
 class Compare:
     def __init__(self, a: IntoFrame, b: IntoFrame) -> None:
+        # Import processing functions from validate module
+        from pointblank.validate import (
+            _process_connection_string,
+            _process_csv_input,
+            _process_parquet_input,
+        )
+
+        # Process input data for table a
+        a = _process_connection_string(a)
+        a = _process_csv_input(a)
+        a = _process_parquet_input(a)
+
+        # Process input data for table b
+        b = _process_connection_string(b)
+        b = _process_csv_input(b)
+        b = _process_parquet_input(b)
+
         self.a: IntoFrame = a
         self.b: IntoFrame = b
 

pointblank/datascan.py

@@ -56,7 +56,8 @@ class DataScan:
     Parameters
     ----------
     data
-        The data to scan and summarize.
+        The data to scan and summarize. This could be a DataFrame object, an Ibis table object,
+        a CSV file path, a Parquet file path, or a database connection string.
     tbl_name
         Optionally, the name of the table could be provided as `tbl_name`.
 
@@ -122,6 +123,23 @@ class DataScan:
 
     # TODO: This needs to be generically typed at the class level, ie. DataScan[T]
     def __init__(self, data: IntoFrameT, tbl_name: str | None = None) -> None:
+        # Import processing functions from validate module
+        from pointblank.validate import (
+            _process_connection_string,
+            _process_csv_input,
+            _process_parquet_input,
+        )
+
+        # Process input data to handle different data source types
+        # Handle connection string input (e.g., "duckdb:///path/to/file.ddb::table_name")
+        data = _process_connection_string(data)
+
+        # Handle CSV file input (e.g., "data.csv" or Path("data.csv"))
+        data = _process_csv_input(data)
+
+        # Handle Parquet file input (e.g., "data.parquet", "data/*.parquet", "data/")
+        data = _process_parquet_input(data)
+
         as_native = nw.from_native(data)
 
         if as_native.implementation.name == "IBIS" and as_native._level == "lazy":
@@ -514,8 +532,9 @@ def col_summary_tbl(data: FrameT | Any, tbl_name: str | None = None) -> GT:
     Parameters
     ----------
     data
-        The table to summarize, which could be a DataFrame object or an Ibis table object. Read the
-        *Supported Input Table Types* section for details on the supported table types.
+        The table to summarize, which could be a DataFrame object, an Ibis table object, a CSV
+        file path, a Parquet file path, or a database connection string. Read the *Supported Input
+        Table Types* section for details on the supported table types.
     tbl_name
         Optionally, the name of the table could be provided as `tbl_name=`.
 
@@ -535,6 +554,10 @@ def col_summary_tbl(data: FrameT | Any, tbl_name: str | None = None) -> GT:
     - PostgreSQL table (`"postgresql"`)*
     - SQLite table (`"sqlite"`)*
     - Parquet table (`"parquet"`)*
+    - CSV files (string path or `pathlib.Path` object with `.csv` extension)
+    - Parquet files (string path, `pathlib.Path` object, glob pattern, directory with `.parquet`
+    extension, or partitioned dataset)
+    - Database connection strings (URI format with optional table specification)
 
     The table types marked with an asterisk need to be prepared as Ibis tables (with type of
     `ibis.expr.types.relations.Table`). Furthermore, using `col_summary_tbl()` with these types of
@@ -566,5 +589,22 @@ def col_summary_tbl(data: FrameT | Any, tbl_name: str | None = None) -> GT:
     ```
     """
 
+    # Import processing functions from validate module
+    from pointblank.validate import (
+        _process_connection_string,
+        _process_csv_input,
+        _process_parquet_input,
+    )
+
+    # Process input data to handle different data source types
+    # Handle connection string input (e.g., "duckdb:///path/to/file.ddb::table_name")
+    data = _process_connection_string(data)
+
+    # Handle CSV file input (e.g., "data.csv" or Path("data.csv"))
+    data = _process_csv_input(data)
+
+    # Handle Parquet file input (e.g., "data.parquet", "data/*.parquet", "data/")
+    data = _process_parquet_input(data)
+
     scanner = DataScan(data=data, tbl_name=tbl_name)
     return scanner.get_tabular_report()