feat(python): Support loading data from multiple Excel/ODS workbooks (#…

…20404)

py-polars/polars/_typing.py

@@ -299,7 +299,7 @@ def fetchmany(self, *args: Any, **kwargs: Any) -> Any:
 # LazyFrame engine selection
 EngineType: TypeAlias = Union[Literal["cpu", "gpu"], "GPUEngine"]
 
-ScanSource: TypeAlias = Union[
+FileSource: TypeAlias = Union[
     str,
     Path,
     IO[bytes],

py-polars/polars/io/avro.py

@@ -29,9 +29,8 @@ def read_avro(
     source
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
-        function, or a `BytesIO` instance).
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        function, or a `BytesIO` instance). For file-like objects, the stream position
+        may not be updated accordingly after reading.
     columns
         Columns to select. Accepts a list of column indices (starting at zero) or a list
         of column names.

py-polars/polars/io/csv/functions.py

@@ -90,9 +90,8 @@ def read_csv(
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
         function, or a `BytesIO` instance). If `fsspec` is installed, it will be used
-        to open remote files.
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        to open remote files. For file-like objects, the stream position may not be
+        updated accordingly after reading.
     has_header
         Indicate if the first row of the dataset is a header or not. If set to False,
         column names will be autogenerated in the following format: `column_x`, with
@@ -764,9 +763,8 @@ def read_csv_batched(
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
         function, or a `BytesIO` instance). If `fsspec` is installed, it will be used
-        to open remote files.
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        to open remote files. For file-like objects, the stream position may not be
+        updated accordingly after reading.
     has_header
         Indicate if the first row of the dataset is a header or not. If set to False,
         column names will be autogenerated in the following format: `column_x`, with

py-polars/polars/io/ipc/functions.py

@@ -62,9 +62,8 @@ def read_ipc(
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
         function, or a `BytesIO` instance). If `fsspec` is installed, it will be used
-        to open remote files.
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        to open remote files. For file-like objects, the stream position may not be
+        updated accordingly after reading.
     columns
         Columns to select. Accepts a list of column indices (starting at zero) or a list
         of column names.
@@ -241,9 +240,8 @@ def read_ipc_stream(
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
         function, or a `BytesIO` instance). If `fsspec` is installed, it will be used
-        to open remote files.
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        to open remote files. For file-like objects, the stream position may not be
+        updated accordingly after reading.
     columns
         Columns to select. Accepts a list of column indices (starting at zero) or a list
         of column names.
@@ -331,9 +329,8 @@ def read_ipc_schema(source: str | Path | IO[bytes] | bytes) -> dict[str, DataTyp
     source
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
-        function, or a `BytesIO` instance).
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        function, or a `BytesIO` instance). For file-like objects, the stream position
+        may not be updated accordingly after reading.
 
     Returns
     -------

py-polars/polars/io/json/read.py

@@ -34,9 +34,8 @@ def read_json(
     source
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
-        function, or a `BytesIO` instance).
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        function, or a `BytesIO` instance). For file-like objects, the stream position
+        may not be updated accordingly after reading.
     schema : Sequence of str, (str,DataType) pairs, or a {str:DataType,} dict
         The DataFrame schema may be declared in several ways:
 

py-polars/polars/io/ndjson.py

@@ -51,9 +51,8 @@ def read_ndjson(
     source
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
-        function, or a `BytesIO` instance).
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        function, or a `BytesIO` instance). For file-like objects, the stream position
+        may not be updated accordingly after reading.
     schema : Sequence of str, (str,DataType) pairs, or a {str:DataType,} dict
         The DataFrame schema may be declared in several ways:
 

py-polars/polars/io/parquet/functions.py

@@ -31,14 +31,14 @@
     from typing import Literal
 
     from polars import DataFrame, DataType, LazyFrame
-    from polars._typing import ParallelStrategy, ScanSource, SchemaDict
+    from polars._typing import FileSource, ParallelStrategy, SchemaDict
     from polars.io.cloud import CredentialProviderFunction
 
 
 @deprecate_renamed_parameter("row_count_name", "row_index_name", version="0.20.4")
 @deprecate_renamed_parameter("row_count_offset", "row_index_offset", version="0.20.4")
 def read_parquet(
-    source: ScanSource,
+    source: FileSource,
     *,
     columns: list[int] | list[str] | None = None,
     n_rows: int | None = None,
@@ -74,7 +74,7 @@ def read_parquet(
 
         File-like objects are supported (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
-        function, or a `BytesIO` instance) For file-like objects, stream position
+        function, or a `BytesIO` instance). For file-like objects, the stream position
         may not be updated accordingly after reading.
     columns
         Columns to select. Accepts a list of column indices (starting at zero) or a list
@@ -304,9 +304,8 @@ def read_parquet_schema(source: str | Path | IO[bytes] | bytes) -> dict[str, Dat
     source
         Path to a file or a file-like object (by "file-like object" we refer to objects
         that have a `read()` method, such as a file handler like the builtin `open`
-        function, or a `BytesIO` instance).
-        For file-like objects,
-        stream position may not be updated accordingly after reading.
+        function, or a `BytesIO` instance). For file-like objects, the stream position
+        may not be updated accordingly after reading.
 
     Returns
     -------
@@ -322,7 +321,7 @@ def read_parquet_schema(source: str | Path | IO[bytes] | bytes) -> dict[str, Dat
 @deprecate_renamed_parameter("row_count_name", "row_index_name", version="0.20.4")
 @deprecate_renamed_parameter("row_count_offset", "row_index_offset", version="0.20.4")
 def scan_parquet(
-    source: ScanSource,
+    source: FileSource,
     *,
     n_rows: int | None = None,
     row_index_name: str | None = None,