Schema#

def apply_hints(self, hints: Schema) -> Schema:
    """Applies hints from another schema to this schema.

    Args:
        hints (Schema): Schema containing hints to apply to this schema.

    Returns:
        Schema: A new Schema with the hints applied.
    """
    return Schema._from_pyschema(self._schema.apply_hints(hints._schema))

def column_names(self) -> list[str]:
    """Returns a list of the names of the columns in the schema.

    Returns:
        list[str]: List of column names in the schema.
    """
    return list(self._schema.names())

def display_with_metadata(self, include_metadata: bool = False) -> str:
    """Returns a string representation of the schema, optionally including metadata."""
    return self._schema.display_with_metadata(include_metadata)

def estimate_row_size_bytes(self) -> float:
    """Estimates the size of a row in bytes based on the schema.

    Returns:
        float: Estimated size of a row in bytes.
    """
    return self._schema.estimate_row_size_bytes()

@classmethod
def from_csv(
    cls,
    path: str,
    parse_options: CsvParseOptions | None = None,
    io_config: IOConfig | None = None,
    multithreaded_io: bool | None = None,
) -> Schema:
    """Creates a Schema from a CSV file.

    Args:
        path (str): Path to the CSV file.
        parse_options (CsvParseOptions | None): Options for parsing the CSV file.
        io_config (IOConfig | None): IO configuration for reading the file.
        multithreaded_io (bool | None): Whether to use multithreaded IO.

    Returns:
        Schema: A Schema object representing the CSV file.
    """
    return Schema._from_pyschema(
        _read_csv_schema(
            uri=path,
            parse_options=parse_options,
            io_config=io_config,
            multithreaded_io=multithreaded_io,
        )
    )

@classmethod
def from_field_name_and_types(cls, fields: list[tuple[str, DataType]]) -> Schema:
    """Creates a Daft Schema from a list of field name and types.

    Args:
        fields (list[tuple[str, DataType]]): List of field name and types

    Returns:
        Schema: Daft schema with the provided field names and types
    """
    return cls._from_field_name_and_types(fields)

@classmethod
def from_json(
    cls,
    path: str,
    parse_options: JsonParseOptions | None = None,
    io_config: IOConfig | None = None,
    multithreaded_io: bool | None = None,
) -> Schema:
    """Creates a Schema from a JSON file.

    Args:
        path (str): Path to the JSON file.
        parse_options (JsonParseOptions | None): Options for parsing the JSON file.
        io_config (IOConfig | None): IO configuration for reading the file.
        multithreaded_io (bool | None): Whether to use multithreaded IO.

    Returns:
        Schema: A Schema object representing the JSON file.
    """
    return Schema._from_pyschema(
        _read_json_schema(
            uri=path,
            parse_options=parse_options,
            io_config=io_config,
            multithreaded_io=multithreaded_io,
        )
    )

@classmethod
def from_parquet(
    cls,
    path: str,
    io_config: IOConfig | None = None,
    multithreaded_io: bool | None = None,
    coerce_int96_timestamp_unit: TimeUnit = TimeUnit.ns(),
) -> Schema:
    """Creates a Schema from a Parquet file.

    Args:
        path (str): Path to the Parquet file.
        io_config (IOConfig | None): IO configuration for reading the file.
        multithreaded_io (bool | None): Whether to use multithreaded IO.
        coerce_int96_timestamp_unit (TimeUnit): The time unit to coerce INT96 timestamps to.

    Returns:
        Schema: A Schema object representing the Parquet file.
    """
    return Schema._from_pyschema(
        _read_parquet_schema(
            uri=path,
            io_config=io_config,
            multithreaded_io=multithreaded_io,
            coerce_int96_timestamp_unit=coerce_int96_timestamp_unit._timeunit,
        )
    )

@classmethod
def from_pyarrow_schema(cls, pa_schema: pa.Schema) -> Schema:
    """Creates a Daft Schema from a PyArrow Schema.

    Args:
        pa_schema (pa.Schema): PyArrow schema to convert

    Returns:
        Schema: Converted Daft schema
    """
    # NOTE: This does not retain schema-level metadata, as Daft Schemas do not have a metadata field.
    fields = []
    for pa_field in pa_schema:
        metadata = None
        if pa_field.metadata:
            metadata = {k.decode(): v.decode() for k, v in pa_field.metadata.items()}
        fields.append(Field.create(pa_field.name, DataType.from_arrow_type(pa_field.type), metadata))
    return cls._from_fields(fields)

@classmethod
def from_pydict(cls, fields: dict[str, DataType]) -> Schema:
    """Creates a Schema from a dictionary of field names and their corresponding DataTypes.

    Args:
        fields (dict[str, DataType]): Dictionary mapping field names to DataTypes.

    Returns:
        Schema: A Schema object created from the provided fields.
    """
    return cls._from_fields([Field.create(k, v) for k, v in fields.items()])

def min_estimated_size_column(self) -> str | None:
    """Returns the name of the column with the minimum estimated size."""
    return self._schema.min_estimated_size_column()

def to_name_set(self) -> set[str]:
    """Returns a set of column names in the schema.

    Returns:
        set[str]: Set of column names in the schema.
    """
    return set(self.column_names())

def to_pyarrow_schema(self) -> pa.Schema:
    """Converts a Daft Schema to a PyArrow Schema.

    Returns:
        pa.Schema: PyArrow schema that corresponds to the provided Daft schema
    """
    _ensure_registered_super_ext_type()
    return self._schema.to_pyarrow_schema()

def union(self, other: Schema) -> Schema:
    """Creates a new Schema that is the union of this schema and another schema.

    Args:
        other (Schema): The schema to union with this schema.

    Returns:
        Schema: A new Schema that is the union of this schema and the other schema.
    """
    if not isinstance(other, Schema):
        raise ValueError(f"Expected Schema, got other: {type(other)}")

    return Schema._from_pyschema(self._schema.union(other._schema))

def apply_hints(self, hints: Schema) -> Schema:
    """Applies hints from another schema to this schema.

    Args:
        hints (Schema): Schema containing hints to apply to this schema.

    Returns:
        Schema: A new Schema with the hints applied.
    """
    return Schema._from_pyschema(self._schema.apply_hints(hints._schema))

def column_names(self) -> list[str]:
    """Returns a list of the names of the columns in the schema.

    Returns:
        list[str]: List of column names in the schema.
    """
    return list(self._schema.names())

def display_with_metadata(self, include_metadata: bool = False) -> str:
    """Returns a string representation of the schema, optionally including metadata."""
    return self._schema.display_with_metadata(include_metadata)

def estimate_row_size_bytes(self) -> float:
    """Estimates the size of a row in bytes based on the schema.

    Returns:
        float: Estimated size of a row in bytes.
    """
    return self._schema.estimate_row_size_bytes()

@classmethod
def from_csv(
    cls,
    path: str,
    parse_options: CsvParseOptions | None = None,
    io_config: IOConfig | None = None,
    multithreaded_io: bool | None = None,
) -> Schema:
    """Creates a Schema from a CSV file.

    Args:
        path (str): Path to the CSV file.
        parse_options (CsvParseOptions | None): Options for parsing the CSV file.
        io_config (IOConfig | None): IO configuration for reading the file.
        multithreaded_io (bool | None): Whether to use multithreaded IO.

    Returns:
        Schema: A Schema object representing the CSV file.
    """
    return Schema._from_pyschema(
        _read_csv_schema(
            uri=path,
            parse_options=parse_options,
            io_config=io_config,
            multithreaded_io=multithreaded_io,
        )
    )

@classmethod
def from_field_name_and_types(cls, fields: list[tuple[str, DataType]]) -> Schema:
    """Creates a Daft Schema from a list of field name and types.

    Args:
        fields (list[tuple[str, DataType]]): List of field name and types

    Returns:
        Schema: Daft schema with the provided field names and types
    """
    return cls._from_field_name_and_types(fields)

@classmethod
def from_json(
    cls,
    path: str,
    parse_options: JsonParseOptions | None = None,
    io_config: IOConfig | None = None,
    multithreaded_io: bool | None = None,
) -> Schema:
    """Creates a Schema from a JSON file.

    Args:
        path (str): Path to the JSON file.
        parse_options (JsonParseOptions | None): Options for parsing the JSON file.
        io_config (IOConfig | None): IO configuration for reading the file.
        multithreaded_io (bool | None): Whether to use multithreaded IO.

    Returns:
        Schema: A Schema object representing the JSON file.
    """
    return Schema._from_pyschema(
        _read_json_schema(
            uri=path,
            parse_options=parse_options,
            io_config=io_config,
            multithreaded_io=multithreaded_io,
        )
    )

@classmethod
def from_parquet(
    cls,
    path: str,
    io_config: IOConfig | None = None,
    multithreaded_io: bool | None = None,
    coerce_int96_timestamp_unit: TimeUnit = TimeUnit.ns(),
) -> Schema:
    """Creates a Schema from a Parquet file.

    Args:
        path (str): Path to the Parquet file.
        io_config (IOConfig | None): IO configuration for reading the file.
        multithreaded_io (bool | None): Whether to use multithreaded IO.
        coerce_int96_timestamp_unit (TimeUnit): The time unit to coerce INT96 timestamps to.

    Returns:
        Schema: A Schema object representing the Parquet file.
    """
    return Schema._from_pyschema(
        _read_parquet_schema(
            uri=path,
            io_config=io_config,
            multithreaded_io=multithreaded_io,
            coerce_int96_timestamp_unit=coerce_int96_timestamp_unit._timeunit,
        )
    )

@classmethod
def from_pyarrow_schema(cls, pa_schema: pa.Schema) -> Schema:
    """Creates a Daft Schema from a PyArrow Schema.

    Args:
        pa_schema (pa.Schema): PyArrow schema to convert

    Returns:
        Schema: Converted Daft schema
    """
    # NOTE: This does not retain schema-level metadata, as Daft Schemas do not have a metadata field.
    fields = []
    for pa_field in pa_schema:
        metadata = None
        if pa_field.metadata:
            metadata = {k.decode(): v.decode() for k, v in pa_field.metadata.items()}
        fields.append(Field.create(pa_field.name, DataType.from_arrow_type(pa_field.type), metadata))
    return cls._from_fields(fields)

@classmethod
def from_pydict(cls, fields: dict[str, DataType]) -> Schema:
    """Creates a Schema from a dictionary of field names and their corresponding DataTypes.

    Args:
        fields (dict[str, DataType]): Dictionary mapping field names to DataTypes.

    Returns:
        Schema: A Schema object created from the provided fields.
    """
    return cls._from_fields([Field.create(k, v) for k, v in fields.items()])

def min_estimated_size_column(self) -> str | None:
    """Returns the name of the column with the minimum estimated size."""
    return self._schema.min_estimated_size_column()

def to_name_set(self) -> set[str]:
    """Returns a set of column names in the schema.

    Returns:
        set[str]: Set of column names in the schema.
    """
    return set(self.column_names())

def to_pyarrow_schema(self) -> pa.Schema:
    """Converts a Daft Schema to a PyArrow Schema.

    Returns:
        pa.Schema: PyArrow schema that corresponds to the provided Daft schema
    """
    _ensure_registered_super_ext_type()
    return self._schema.to_pyarrow_schema()

def union(self, other: Schema) -> Schema:
    """Creates a new Schema that is the union of this schema and another schema.

    Args:
        other (Schema): The schema to union with this schema.

    Returns:
        Schema: A new Schema that is the union of this schema and the other schema.
    """
    if not isinstance(other, Schema):
        raise ValueError(f"Expected Schema, got other: {type(other)}")

    return Schema._from_pyschema(self._schema.union(other._schema))