Python: Fix D401 pydocstyle issues (apache#8401)

* Fix D401 pydocstyle issues

* Update python/tests/conftest.py

---------

Co-authored-by: Fokko Driesprong <[email protected]>

python/.pre-commit-config.yaml

@@ -91,7 +91,7 @@ repos:
       - id: pydocstyle
         args:
           [
-            "--ignore=D100,D102,D101,D103,D104,D106,D107,D203,D212,D213,D401,D404,D405,D406,D407,D411,D413,D415,D417",
+            "--ignore=D100,D102,D101,D103,D104,D106,D107,D203,D212,D213,D404,D405,D406,D407,D411,D413,D415,D417",
           ]
         additional_dependencies:
           - tomli==2.0.1

python/pyiceberg/avro/decoder.py

@@ -47,15 +47,15 @@ def skip(self, n: int) -> None:
         """Skip n bytes."""
 
     def read_boolean(self) -> bool:
-        """Reads a value from the stream as a boolean.
+        """Read a value from the stream as a boolean.
 
         A boolean is written as a single byte
         whose value is either 0 (false) or 1 (true).
         """
         return ord(self.read(1)) == 1
 
     def read_int(self) -> int:
-        """Reads an int/long value.
+        """Read an int/long value.
 
         int/long values are written using variable-length, zigzag coding.
         """
@@ -70,18 +70,18 @@ def read_int(self) -> int:
         return datum
 
     def read_ints(self, n: int) -> Tuple[int, ...]:
-        """Reads a list of integers."""
+        """Read a list of integers."""
         return tuple(self.read_int() for _ in range(n))
 
     def read_int_bytes_dict(self, n: int, dest: Dict[int, bytes]) -> None:
-        """Reads a dictionary of integers for keys and bytes for values into a destination dictionary."""
+        """Read a dictionary of integers for keys and bytes for values into a destination dictionary."""
         for _ in range(n):
             k = self.read_int()
             v = self.read_bytes()
             dest[k] = v
 
     def read_float(self) -> float:
-        """Reads a value from the stream as a float.
+        """Read a value from the stream as a float.
 
         A float is written as 4 bytes.
         The float is converted into a 32-bit integer using a method equivalent to
@@ -90,7 +90,7 @@ def read_float(self) -> float:
         return float(cast(Tuple[float, ...], STRUCT_FLOAT.unpack(self.read(4)))[0])
 
     def read_double(self) -> float:
-        """Reads a value from the stream as a double.
+        """Read a value from the stream as a double.
 
         A double is written as 8 bytes.
         The double is converted into a 64-bit integer using a method equivalent to
@@ -104,7 +104,7 @@ def read_bytes(self) -> bytes:
         return self.read(num_bytes) if num_bytes > 0 else b""
 
     def read_utf8(self) -> str:
-        """Reads an utf-8 encoded string from the stream.
+        """Read an utf-8 encoded string from the stream.
 
         A string is encoded as a long followed by
         that many bytes of UTF-8 encoded character data.

python/pyiceberg/avro/encoder.py

@@ -32,7 +32,7 @@ def write(self, b: bytes) -> None:
         self._output_stream.write(b)
 
     def write_boolean(self, boolean: bool) -> None:
-        """A boolean is written as a single byte whose value is either 0 (false) or 1 (true).
+        """Write a boolean as a single byte whose value is either 0 (false) or 1 (true).
 
         Args:
             boolean: The boolean to write.
@@ -48,11 +48,11 @@ def write_int(self, integer: int) -> None:
         self.write(bytearray([datum]))
 
     def write_float(self, f: float) -> None:
-        """A float is written as 4 bytes."""
+        """Write a float as 4 bytes."""
         self.write(STRUCT_FLOAT.pack(f))
 
     def write_double(self, f: float) -> None:
-        """A double is written as 8 bytes."""
+        """Write a double as 8 bytes."""
         self.write(STRUCT_DOUBLE.pack(f))
 
     def write_bytes(self, b: bytes) -> None:
@@ -61,7 +61,7 @@ def write_bytes(self, b: bytes) -> None:
         self.write(b)
 
     def write_utf8(self, s: str) -> None:
-        """A string is encoded as a long followed by that many bytes of UTF-8 encoded character data."""
+        """Encode a string as a long followed by that many bytes of UTF-8 encoded character data."""
         self.write_bytes(s.encode("utf-8"))
 
     def write_uuid(self, uuid: UUID) -> None:

python/pyiceberg/avro/file.py

@@ -109,14 +109,14 @@ class Block(Generic[D]):
     position: int = 0
 
     def __iter__(self) -> Block[D]:
-        """Returns an iterator for the Block class."""
+        """Return an iterator for the Block class."""
         return self
 
     def has_next(self) -> bool:
         return self.position < self.block_records
 
     def __next__(self) -> D:
-        """Returns the next item when iterating over the Block class."""
+        """Return the next item when iterating over the Block class."""
         if self.has_next():
             self.position += 1
             return self.reader.read(self.block_decoder)
@@ -160,9 +160,9 @@ def __init__(
         self.block = None
 
     def __enter__(self) -> AvroFile[D]:
-        """Generates a reader tree for the payload within an avro file.
+        """Generate a reader tree for the payload within an avro file.
 
-        Returns:
+        Return:
             A generator returning the AvroStructs.
         """
         with self.input_file.open() as f:
@@ -179,10 +179,10 @@ def __enter__(self) -> AvroFile[D]:
     def __exit__(
         self, exctype: Optional[Type[BaseException]], excinst: Optional[BaseException], exctb: Optional[TracebackType]
     ) -> None:
-        """Performs cleanup when exiting the scope of a 'with' statement."""
+        """Perform cleanup when exiting the scope of a 'with' statement."""
 
     def __iter__(self) -> AvroFile[D]:
-        """Returns an iterator for the AvroFile class."""
+        """Return an iterator for the AvroFile class."""
         return self
 
     def _read_block(self) -> int:
@@ -202,7 +202,7 @@ def _read_block(self) -> int:
         return block_records
 
     def __next__(self) -> D:
-        """Returns the next item when iterating over the AvroFile class."""
+        """Return the next item when iterating over the AvroFile class."""
         if self.block and self.block.has_next():
             return next(self.block)
 
@@ -238,7 +238,7 @@ def __init__(self, output_file: OutputFile, schema: Schema, schema_name: str, me
 
     def __enter__(self) -> AvroOutputFile[D]:
         """
-        Opens the file and writes the header.
+        Open the file and writes the header.
 
         Returns:
             The file object to write records to
@@ -254,7 +254,7 @@ def __enter__(self) -> AvroOutputFile[D]:
     def __exit__(
         self, exctype: Optional[Type[BaseException]], excinst: Optional[BaseException], exctb: Optional[TracebackType]
     ) -> None:
-        """Performs cleanup when exiting the scope of a 'with' statement."""
+        """Perform cleanup when exiting the scope of a 'with' statement."""
         self.output_stream.close()
 
     def _write_header(self) -> None:

python/pyiceberg/avro/reader.py

@@ -97,7 +97,7 @@ def skip(self, decoder: ReadableDecoder) -> None:
         ...
 
     def __repr__(self) -> str:
-        """Returns the string representation of the Reader class."""
+        """Return the string representation of the Reader class."""
         return f"{self.__class__.__name__}()"
 
 
@@ -217,11 +217,11 @@ def skip(self, decoder: ReadableDecoder) -> None:
         decoder.skip(len(self))
 
     def __len__(self) -> int:
-        """Returns the length of an instance of the FixedReader class."""
+        """Return the length of an instance of the FixedReader class."""
         return self._len
 
     def __repr__(self) -> str:
-        """Returns the string representation of the FixedReader class."""
+        """Return the string representation of the FixedReader class."""
         return f"FixedReader({self._len})"
 
 
@@ -263,7 +263,7 @@ def skip(self, decoder: ReadableDecoder) -> None:
         decoder.skip_bytes()
 
     def __repr__(self) -> str:
-        """Returns the string representation of the DecimalReader class."""
+        """Return the string representation of the DecimalReader class."""
         return f"DecimalReader({self.precision}, {self.scale})"
 
 
@@ -346,19 +346,19 @@ def skip(self, decoder: ReadableDecoder) -> None:
             field.skip(decoder)
 
     def __eq__(self, other: Any) -> bool:
-        """Returns the equality of two instances of the StructReader class."""
+        """Return the equality of two instances of the StructReader class."""
         return (
             self.field_readers == other.field_readers and self.create_struct == other.create_struct
             if isinstance(other, StructReader)
             else False
         )
 
     def __repr__(self) -> str:
-        """Returns the string representation of the StructReader class."""
+        """Return the string representation of the StructReader class."""
         return f"StructReader(({','.join(repr(field) for field in self.field_readers)}), {repr(self.create_struct)})"
 
     def __hash__(self) -> int:
-        """Returns a hashed representation of the StructReader class."""
+        """Return a hashed representation of the StructReader class."""
         return self._hash
 
 
@@ -392,7 +392,7 @@ def skip(self, decoder: ReadableDecoder) -> None:
         _skip_map_array(decoder, lambda: self.element.skip(decoder))
 
     def __hash__(self) -> int:
-        """Returns a hashed representation of the ListReader class."""
+        """Return a hashed representation of the ListReader class."""
         return self._hash
 
 
@@ -492,5 +492,5 @@ def skip() -> None:
         _skip_map_array(decoder, skip)
 
     def __hash__(self) -> int:
-        """Returns a hashed representation of the MapReader class."""
+        """Return a hashed representation of the MapReader class."""
         return self._hash

python/pyiceberg/avro/resolver.py

@@ -108,7 +108,7 @@
 def construct_reader(
     file_schema: Union[Schema, IcebergType], read_types: Dict[int, Callable[..., StructProtocol]] = EMPTY_DICT
 ) -> Reader:
-    """Constructs a reader from a file schema.
+    """Construct a reader from a file schema.
 
     Args:
         file_schema (Schema | IcebergType): The schema of the Avro file.
@@ -120,7 +120,7 @@ def construct_reader(
 
 
 def construct_writer(file_schema: Union[Schema, IcebergType]) -> Writer:
-    """Constructs a writer from a file schema.
+    """Construct a writer from a file schema.
 
     Args:
         file_schema (Schema | IcebergType): The schema of the Avro file.
@@ -132,7 +132,7 @@ def construct_writer(file_schema: Union[Schema, IcebergType]) -> Writer:
 
 
 class ConstructWriter(SchemaVisitorPerPrimitiveType[Writer]):
-    """Constructs a writer tree from an Iceberg schema."""
+    """Construct a writer tree from an Iceberg schema."""
 
     def schema(self, schema: Schema, struct_result: Writer) -> Writer:
         return struct_result
@@ -198,7 +198,7 @@ def resolve(
     read_types: Dict[int, Callable[..., StructProtocol]] = EMPTY_DICT,
     read_enums: Dict[int, Callable[..., Enum]] = EMPTY_DICT,
 ) -> Reader:
-    """Resolves the file and read schema to produce a reader.
+    """Resolve the file and read schema to produce a reader.
 
     Args:
         file_schema (Schema | IcebergType): The schema of the Avro file.

python/pyiceberg/avro/writer.py

@@ -45,7 +45,7 @@ def write(self, encoder: BinaryEncoder, val: Any) -> Any:
         ...
 
     def __repr__(self) -> str:
-        """Returns string representation of this object."""
+        """Return string representation of this object."""
         return f"{self.__class__.__name__}()"
 
 
@@ -116,11 +116,11 @@ def write(self, encoder: BinaryEncoder, val: bytes) -> None:
         encoder.write(val)
 
     def __len__(self) -> int:
-        """Returns the length of this object."""
+        """Return the length of this object."""
         return self._len
 
     def __repr__(self) -> str:
-        """Returns string representation of this object."""
+        """Return string representation of this object."""
         return f"FixedWriter({self._len})"
 
 
@@ -140,7 +140,7 @@ def write(self, encoder: BinaryEncoder, val: Any) -> None:
         return encoder.write(decimal_to_bytes(val, byte_length=decimal_required_bytes(self.precision)))
 
     def __repr__(self) -> str:
-        """Returns string representation of this object."""
+        """Return string representation of this object."""
         return f"DecimalWriter({self.precision}, {self.scale})"
 
 
@@ -165,15 +165,15 @@ def write(self, encoder: BinaryEncoder, val: StructType) -> None:
             writer.write(encoder, value)
 
     def __eq__(self, other: Any) -> bool:
-        """Implements the equality operator for this object."""
+        """Implement the equality operator for this object."""
         return self.field_writers == other.field_writers if isinstance(other, StructWriter) else False
 
     def __repr__(self) -> str:
-        """Returns string representation of this object."""
+        """Return string representation of this object."""
         return f"StructWriter({','.join(repr(field) for field in self.field_writers)})"
 
     def __hash__(self) -> int:
-        """Returns the hash of the writer as hash of this object."""
+        """Return the hash of the writer as hash of this object."""
         return hash(self.field_writers)