Closes #5183: Increase Literals typing through project

arkouda/numpy/pdarrayclass.py

@@ -6,7 +6,7 @@
 from functools import reduce
 from math import ceil
 from sys import modules
-from typing import TYPE_CHECKING, List, Optional, Tuple, Union, cast, overload
+from typing import TYPE_CHECKING, List, Literal, Optional, Tuple, Union, cast, overload
 
 import numpy as np
 
@@ -2831,7 +2831,7 @@ def to_parquet(
         self,
         prefix_path: str,
         dataset: str = "array",
-        mode: str = "truncate",
+        mode: Literal["truncate", "append"] = "truncate",
         compression: Optional[str] = None,
     ) -> str:
         """
@@ -2846,7 +2846,7 @@ def to_parquet(
             Directory and filename prefix that all output files share
         dataset : str
             Name of the dataset to create in files (must not already exist)
-        mode : str {'truncate' | 'append'}
+        mode : {'truncate', 'append'}
             By default, truncate (overwrite) output files, if they exist.
             If 'append', attempt to create new dataset in existing files.
         compression : str (Optional)
@@ -2914,8 +2914,8 @@ def to_hdf(
         self,
         prefix_path: str,
         dataset: str = "array",
-        mode: str = "truncate",
-        file_type: str = "distribute",
+        mode: Literal["truncate", "append"] = "truncate",
+        file_type: Literal["single", "distribute"] = "distribute",
     ) -> str:
         """
         Save the pdarray to HDF5.
@@ -2927,10 +2927,10 @@ def to_hdf(
             Directory and filename prefix that all output files share
         dataset : str
             Name of the dataset to create in files (must not already exist)
-        mode : str {'truncate' | 'append'}
+        mode : {'truncate', 'append'}
             By default, truncate (overwrite) output files, if they exist.
             If 'append', attempt to create new dataset in existing files.
-        file_type: str ("single" | "distribute")
+        file_type: {"single", "distribute"}
             Default: "distribute"
             When set to single, dataset is written to a single file.
             When distribute, dataset is written on a file per locale.

arkouda/numpy/segarray.py

@@ -838,8 +838,8 @@ def to_hdf(
         self,
         prefix_path,
         dataset="segarray",
-        mode="truncate",
-        file_type="distribute",
+        mode: Literal["truncate", "append"] = "truncate",
+        file_type: Literal["single", "distribute"] = "distribute",
     ):
         """
         Save the SegArray to HDF5. The result is a collection of HDF5 files, one file

arkouda/numpy/timeclass.py

@@ -1,7 +1,7 @@
 import datetime
 import json
 
-from typing import Optional, Union
+from typing import Literal, Optional, Union
 
 import numpy as np
 
@@ -226,8 +226,8 @@ def to_hdf(
         self,
         prefix_path: str,
         dataset: str = "array",
-        mode: str = "truncate",
-        file_type: str = "distribute",
+        mode: Literal["truncate", "append"] = "truncate",
+        file_type: Literal["single", "distribute"] = "distribute",
     ):
         """Override of the pdarray to_hdf to store the special dtype."""
         from arkouda.client import generic_msg

arkouda/pandas/categorical.py

@@ -56,6 +56,7 @@
     Any,
     Dict,
     List,
+    Literal,
     Optional,
     Sequence,
     Tuple,
@@ -1233,8 +1234,8 @@ def to_hdf(
         self,
         prefix_path,
         dataset="categorical_array",
-        mode="truncate",
-        file_type="distribute",
+        mode: Literal["truncate", "append"] = "truncate",
+        file_type: Literal["single", "distribute"] = "distribute",
     ):
         """
         Save the Categorical to HDF5.

arkouda/pandas/dataframe.py

@@ -55,6 +55,7 @@
     Callable,
     Dict,
     List,
+    Literal,
     Optional,
     Tuple,
     TypeVar,
@@ -2782,7 +2783,9 @@ def _prep_data(self, index=False, columns=None):
             data["Index"] = self.index.values
         return data
 
-    def to_hdf(self, path, index=False, columns=None, file_type="distribute"):
+    def to_hdf(
+        self, path, index=False, columns=None, file_type: Literal["single", "distribute"] = "distribute"
+    ):
         """
         Save DataFrame to disk as hdf5, preserving column names.
 

arkouda/pandas/groupbyclass.py

@@ -50,6 +50,7 @@
     TYPE_CHECKING,
     Dict,
     List,
+    Literal,
     Optional,
     Sequence,
     Tuple,
@@ -470,8 +471,8 @@ def to_hdf(
         self,
         prefix_path,
         dataset="groupby",
-        mode="truncate",
-        file_type="distribute",
+        mode: Literal["truncate", "append"] = "truncate",
+        file_type: Literal["single", "distribute"] = "distribute",
     ):
         """
         Save the GroupBy to HDF5.

arkouda/pandas/io.py

@@ -1561,20 +1561,24 @@ def to_hdf(
             mode = "append"
 
 
-def _get_hdf_filetype(filename: str) -> str:
+def _get_hdf_filetype(filename: str) -> Literal["single", "distribute"]:
     from arkouda.client import generic_msg
 
     if not (filename and filename.strip()):
         raise ValueError("filename cannot be an empty string")
 
     cmd = "hdffileformat"
-    return cast(
+    result = cast(
         str,
         generic_msg(
             cmd=cmd,
             args={"filename": filename},
         ),
     )
+    if result not in ("single", "distribute"):
+        raise ValueError(f"Unexpected file type: {result!r}")
+
+    return cast(Literal["single", "distribute"], result)
 
 
 def _repack_hdf(prefix_path: str):