def _add_query_metadata_generator(
dfs: Iterator[pd.DataFrame],
query_metadata: _QueryMetadata) -> Iterator[pd.DataFrame]:
"""Add Query Execution metadata to every DF in iterator."""
for df in dfs:
df = _apply_query_metadata(df=df, query_metadata=query_metadata)
yield df
def _fetch_csv_result(
query_metadata: _QueryMetadata,
keep_files: bool,
chunksize: Optional[int],
use_threads: bool,
boto3_session: boto3.Session,
s3_additional_kwargs: Optional[Dict[str, Any]],
) -> Union[pd.DataFrame, Iterator[pd.DataFrame]]:
_chunksize: Optional[int] = chunksize if isinstance(chunksize,
int) else None
_logger.debug("_chunksize: %s", _chunksize)
if query_metadata.output_location is None or query_metadata.output_location.endswith(
".csv") is False:
chunked = _chunksize is not None
return _empty_dataframe_response(chunked, query_metadata)
path: str = query_metadata.output_location
_logger.debug("Start CSV reading from %s", path)
ret = s3.read_csv(
path=[path],
dtype=query_metadata.dtype,
parse_dates=query_metadata.parse_timestamps,
converters=query_metadata.converters,
quoting=csv.QUOTE_ALL,
keep_default_na=False,
na_values=["", "NaN"],
chunksize=_chunksize,
skip_blank_lines=False,
use_threads=False,
boto3_session=boto3_session,
)
_logger.debug("Start type casting...")
_logger.debug(type(ret))
if _chunksize is None:
df = _fix_csv_types(df=ret,
parse_dates=query_metadata.parse_dates,
binaries=query_metadata.binaries)
df = _apply_query_metadata(df=df, query_metadata=query_metadata)
if keep_files is False:
s3.delete_objects(
path=[path, f"{path}.metadata"],
use_threads=use_threads,
boto3_session=boto3_session,
s3_additional_kwargs=s3_additional_kwargs,
)
return df
dfs = _fix_csv_types_generator(dfs=ret,
parse_dates=query_metadata.parse_dates,
binaries=query_metadata.binaries)
dfs = _add_query_metadata_generator(dfs=dfs, query_metadata=query_metadata)
if keep_files is False:
return _delete_after_iterate(
dfs=dfs,
paths=[path, f"{path}.metadata"],
use_threads=use_threads,
boto3_session=boto3_session,
s3_additional_kwargs=s3_additional_kwargs,
)
return dfs
def _fetch_parquet_result(
query_metadata: _QueryMetadata,
keep_files: bool,
categories: Optional[List[str]],
chunksize: Optional[int],
use_threads: bool,
boto3_session: boto3.Session,
s3_additional_kwargs: Optional[Dict[str, Any]],
) -> Union[pd.DataFrame, Iterator[pd.DataFrame]]:
ret: Union[pd.DataFrame, Iterator[pd.DataFrame]]
chunked: Union[bool, int] = False if chunksize is None else chunksize
_logger.debug("chunked: %s", chunked)
if query_metadata.manifest_location is None:
return _empty_dataframe_response(bool(chunked), query_metadata)
manifest_path: str = query_metadata.manifest_location
metadata_path: str = manifest_path.replace("-manifest.csv", ".metadata")
_logger.debug("manifest_path: %s", manifest_path)
_logger.debug("metadata_path: %s", metadata_path)
paths: List[str] = _extract_ctas_manifest_paths(
path=manifest_path, boto3_session=boto3_session)
if not paths:
return _empty_dataframe_response(bool(chunked), query_metadata)
ret = s3.read_parquet(
path=paths,
use_threads=use_threads,
boto3_session=boto3_session,
chunked=chunked,
categories=categories,
ignore_index=True,
)
if chunked is False:
ret = _apply_query_metadata(df=ret, query_metadata=query_metadata)
else:
ret = _add_query_metadata_generator(dfs=ret,
query_metadata=query_metadata)
paths_delete: List[str] = paths + [manifest_path, metadata_path]
_logger.debug("type(ret): %s", type(ret))
if chunked is False:
if keep_files is False:
s3.delete_objects(
path=paths_delete,
use_threads=use_threads,
boto3_session=boto3_session,
s3_additional_kwargs=s3_additional_kwargs,
)
return ret
if keep_files is False:
return _delete_after_iterate(
dfs=ret,
paths=paths_delete,
use_threads=use_threads,
boto3_session=boto3_session,
s3_additional_kwargs=s3_additional_kwargs,
)
return ret
def _fetch_parquet_result(
query_metadata: _QueryMetadata,
keep_files: bool,
categories: Optional[List[str]],
chunksize: Optional[int],
use_threads: bool,
boto3_session: boto3.Session,
s3_additional_kwargs: Optional[Dict[str, Any]],
temp_table_fqn: Optional[str] = None,
) -> Union[pd.DataFrame, Iterator[pd.DataFrame]]:
ret: Union[pd.DataFrame, Iterator[pd.DataFrame]]
chunked: Union[bool, int] = False if chunksize is None else chunksize
_logger.debug("chunked: %s", chunked)
if query_metadata.manifest_location is None:
return _empty_dataframe_response(bool(chunked), query_metadata)
manifest_path: str = query_metadata.manifest_location
metadata_path: str = manifest_path.replace("-manifest.csv", ".metadata")
_logger.debug("manifest_path: %s", manifest_path)
_logger.debug("metadata_path: %s", metadata_path)
paths: List[str] = _extract_ctas_manifest_paths(path=manifest_path, boto3_session=boto3_session)
if not paths:
if not temp_table_fqn:
raise exceptions.EmptyDataFrame("Query would return untyped, empty dataframe.")
database, temp_table_name = map(lambda x: x.replace('"', ""), temp_table_fqn.split("."))
dtype_dict = catalog.get_table_types(database=database, table=temp_table_name)
df = pd.DataFrame(columns=list(dtype_dict.keys()))
df = cast_pandas_with_athena_types(df=df, dtype=dtype_dict)
df = _apply_query_metadata(df=df, query_metadata=query_metadata)
return df
ret = s3.read_parquet(
path=paths,
use_threads=use_threads,
boto3_session=boto3_session,
chunked=chunked,
categories=categories,
ignore_index=True,
)
if chunked is False:
ret = _apply_query_metadata(df=ret, query_metadata=query_metadata)
else:
ret = _add_query_metadata_generator(dfs=ret, query_metadata=query_metadata)
paths_delete: List[str] = paths + [manifest_path, metadata_path]
_logger.debug("type(ret): %s", type(ret))
if chunked is False:
if keep_files is False:
s3.delete_objects(
path=paths_delete,
use_threads=use_threads,
boto3_session=boto3_session,
s3_additional_kwargs=s3_additional_kwargs,
)
return ret
if keep_files is False:
return _delete_after_iterate(
dfs=ret,
paths=paths_delete,
use_threads=use_threads,
boto3_session=boto3_session,
s3_additional_kwargs=s3_additional_kwargs,
)
return ret
