MCPcopy Create free account
hub / github.com/apache/arrow / _filesystem_dataset

Function _filesystem_dataset

python/pyarrow/dataset.py:442–482  ·  view source on GitHub ↗

Create a FileSystemDataset which can be used to build a Dataset. Parameters are documented in the dataset function. Returns ------- FileSystemDataset

(source, schema=None, filesystem=None,
                        partitioning=None, format=None,
                        partition_base_dir=None, exclude_invalid_files=None,
                        selector_ignore_prefixes=None)

Source from the content-addressed store, hash-verified

440
441
442def _filesystem_dataset(source, schema=None, filesystem=None,
443 partitioning=None, format=None,
444 partition_base_dir=None, exclude_invalid_files=None,
445 selector_ignore_prefixes=None):
446 """
447 Create a FileSystemDataset which can be used to build a Dataset.
448
449 Parameters are documented in the dataset function.
450
451 Returns
452 -------
453 FileSystemDataset
454 """
455 from pyarrow.fs import LocalFileSystem, _ensure_filesystem, FileInfo
456
457 format = _ensure_format(format or 'parquet')
458 partitioning = _ensure_partitioning(partitioning)
459
460 if isinstance(source, (list, tuple)):
461 if source and isinstance(source[0], FileInfo):
462 if filesystem is None:
463 # fall back to local file system as the default
464 fs = LocalFileSystem()
465 else:
466 # construct a filesystem if it is a valid URI
467 fs = _ensure_filesystem(filesystem)
468 paths_or_selector = source
469 else:
470 fs, paths_or_selector = _ensure_multiple_sources(source, filesystem)
471 else:
472 fs, paths_or_selector = _ensure_single_source(source, filesystem)
473
474 options = FileSystemFactoryOptions(
475 partitioning=partitioning,
476 partition_base_dir=partition_base_dir,
477 exclude_invalid_files=exclude_invalid_files,
478 selector_ignore_prefixes=selector_ignore_prefixes
479 )
480 factory = FileSystemDatasetFactory(fs, paths_or_selector, format, options)
481
482 return factory.finish(schema)
483
484
485def _in_memory_dataset(source, schema=None, **kwargs):

Callers 1

datasetFunction · 0.85

Calls 9

_ensure_filesystemFunction · 0.90
_ensure_formatFunction · 0.85
_ensure_partitioningFunction · 0.85
LocalFileSystemClass · 0.85
_ensure_multiple_sourcesFunction · 0.85
_ensure_single_sourceFunction · 0.85
finishMethod · 0.45

Tested by

no test coverage detected