def __init__(self,
in_blocks: BlockList,
stats: DatasetStats,
dataset_uuid=None):
"""Create a plan with no transformation stages.
Args:
in_blocks: Base list of blocks.
stats: Stats for the base blocks.
dataset_uuid: Dataset's UUID.
"""
self._in_blocks = in_blocks
self._in_stats = stats
# A computed snapshot of some prefix of stages.
self._snapshot_blocks = None
self._snapshot_stats = None
# Chains of stages.
self._stages_before_snapshot = []
self._stages_after_snapshot = []
# Cache of optimized stages.
self._last_optimized_stages = None
self._dataset_uuid = dataset_uuid or uuid.uuid4().hex
if not stats.dataset_uuid:
stats.dataset_uuid = self._dataset_uuid
def _rewrite_read_stages(
blocks: BlockList,
stats: DatasetStats,
stages: List[Stage],
dataset_uuid: str,
) -> Tuple[BlockList, DatasetStats, List[Stage]]:
"""Rewrites read stages into one-to-one stages, if needed."""
if _is_lazy(blocks) and stages:
blocks, stats, stage = _rewrite_read_stage(blocks)
stats.dataset_uuid = dataset_uuid
stages.insert(0, stage)
return blocks, stats, stages
def __init__(self,
in_blocks: BlockList,
stats: DatasetStats,
dataset_uuid=None):
"""Create a plan with no transformation stages.
Args:
in_blocks: Base list of blocks.
stats: Stats for the base blocks.
"""
self._in_blocks = in_blocks
self._out_blocks = None
self._in_stats = stats
self._out_stats = None
self._stages = []
self._dataset_uuid = dataset_uuid or uuid.uuid4().hex
if not stats.dataset_uuid:
stats.dataset_uuid = self._dataset_uuid
