Function write_metadata

python/pyarrow/parquet/core.py:2297–2366

Write metadata-only Parquet file from schema. This can be used with `write_to_dataset` to generate `_common_metadata` and `_metadata` sidecar files. Parameters ---------- schema : pyarrow.Schema where : string or pyarrow.NativeFile metadata_collector : list

(schema, where, metadata_collector=None, filesystem=None,
                   **kwargs)

def write_metadata(schema, where, metadata_collector=None, filesystem=None,
                   **kwargs):
    """
    Write metadata-only Parquet file from schema. This can be used with
    `write_to_dataset` to generate `_common_metadata` and `_metadata` sidecar
    files.

    Parameters
    ----------
    schema : pyarrow.Schema
    where : string or pyarrow.NativeFile
    metadata_collector : list
        where to collect metadata information.
    filesystem : FileSystem, default None
        If nothing passed, will be inferred from `where` if path-like, else
        `where` is already a file-like object so no filesystem is needed.
    **kwargs : dict,
        Additional kwargs for ParquetWriter class. See docstring for
        `ParquetWriter` for more information.

    Examples
    --------
    Generate example data:

    >>> import pyarrow as pa
    >>> table = pa.table({'n_legs': [2, 2, 4, 4, 5, 100],
    ...                   'animal': ["Flamingo", "Parrot", "Dog", "Horse",
    ...                              "Brittle stars", "Centipede"]})

    Write a dataset and collect metadata information.

    >>> metadata_collector = []
    >>> import pyarrow.parquet as pq
    >>> pq.write_to_dataset(
    ...     table, 'dataset_metadata',
    ...      metadata_collector=metadata_collector)

    Write the `_common_metadata` parquet file without row groups statistics.

    >>> pq.write_metadata(
    ...     table.schema, 'dataset_metadata/_common_metadata')

    Write the `_metadata` parquet file with row groups statistics.

    >>> pq.write_metadata(
    ...     table.schema, 'dataset_metadata/_metadata',
    ...     metadata_collector=metadata_collector)
    """
    filesystem, where = _resolve_filesystem_and_path(where, filesystem)

    if hasattr(where, "seek"):  # file-like
        cursor_position = where.tell()

    writer = ParquetWriter(where, schema, filesystem, **kwargs)
    writer.close()

    if metadata_collector is not None:
        # ParquetWriter doesn't expose the metadata until it's written. Write