File List HWM#
- class etl_entities.old_hwm.file_list_hwm.FileListHWM(*, source: <pydantic.v1.fields.DeferredType object at 0x7ffb11e24170>, value: ~typing.FrozenSet[~etl_entities.instance.path.relative_path.RelativePath] = None, modified_time: <pydantic.v1.fields.DeferredType object at 0x7ffb11e24440> = None, process: <pydantic.v1.fields.DeferredType object at 0x7ffb11e24560> = None)#
File List HWM type
Deprecated since version 2.0.0: Use
etl_entities.hwm.file.file_list_hwm.FileListHWM
instead- Parameters:
- source
etl_entities.instance.path.remote_folder.RemoteFolder
Folder instance
- value
frozenset
ofpathlib.PosixPath
, default: empty set HWM value
- modified_time
datetime.datetime
, default: current datetime HWM value modification time
- process
etl_entities.process.process.Process
, default: current process Process instance
- source
Examples
from etl_entities.old_hwm import FileListHWM from etl_entities.source import RemoteFolder folder = RemoteFolder(name="/absolute/path", instance="ftp://ftp.server:21") old_hwm = FileListHWM( source=folder, value=["some/path", "another.file"], )
- __abs__() frozenset[AbsolutePath] #
Returns set of files with absolute paths
- Returns:
- result
frosenzet
ofpathlib.PosixPath
Copy of HWM with updated value
- result
Examples
from etl_entities.old_hwm import FileListHWM from etl_entities.source import RemoteFolder from etl_entities.instance import AbsolutePath old_hwm = FileListHWM( value=["some/path"], source=RemoteFolder(name="/absolute/path", ...), ... ) assert abs(old_hwm) == frozenset(AbsolutePath("/absolute/path/some/path"))
- __add__(value: str | PathLike | Iterable[str | PathLike])#
Adds path or paths to HWM value, and return copy of HWM
- Parameters:
- value
str
orpathlib.PosixPath
ortyping.Iterable
of them Path or collection of paths to be added to value
- value
- Returns:
- resultFileListHWM
HWM copy with new value
Examples
from etl_entities.old_hwm import FileListHWM hwm1 = FileListHWM(value=["some/path"], ...) hwm2 = FileListHWM(value=["some/path", "another.file"], ...) assert hwm1 + "another.file" == hwm2 # same as FileListHWM(value=hwm1.value + "another.file", ...)
- __bool__()#
Check if HWM value is set
- Returns:
- resultbool
False
ifvalue
is empty,True
otherwise
Examples
from etl_entities.old_hwm import FileListHWM old_hwm = FileListHWM(value=["some/path.py"], ...) assert old_hwm # same as bool(old_hwm.value) old_hwm = FileListHWM(value=[], ...) assert not old_hwm
- __contains__(item)#
Checks if path is present in value
- Returns:
- resultbool
True
if path is present in value,False
otherwise
Examples
from etl_entities.old_hwm import FileListHWM from etl_entities.source import RemoteFolder from etl_entities.instance import AbsolutePath old_hwm = FileListHWM( value=["some/path"], source=Folder(name="/absolute/path", ...), ... ) assert "some/path" in old_hwm assert "/absolute/path/some/path" in old_hwm
- __iter__()#
Iterate over files in FileListHWM.
- Returns:
- resultIterator[RelativePath]
Files in HWM, order is not preserved
Examples
from etl_entities.old_hwm import FileListHWM from etl_entities.instance import RelativePath hwm1 = FileListHWM(value=["some", "another"], ...) hwm2 = FileListHWM(value=[], ...) assert set(hwm1) == {RelativePath("some"), RelativePath("another")} assert set(hwm2) == set()
- __len__()#
Return number of files in the HWM.
- Returns:
- resultint
Number of files
Examples
from etl_entities.old_hwm import FileListHWM hwm1 = FileListHWM(value=["some", "another"], ...) hwm2 = FileListHWM(value=[], ...) assert len(hwm1) == 2 assert len(hwm2) == 0
- __sub__(value: str | PathLike | Iterable[str | PathLike])#
Remove path or paths from HWM value, and return copy of HWM
- Parameters:
- value
str
orpathlib.PosixPath
ortyping.Iterable
of them Path or collection of paths to be added to value
- value
- Returns:
- resultFileListHWM
HWM copy with new value
Examples
from etl_entities.old_hwm import FileListHWM hwm1 = FileListHWM(value=["some/path"], ...) hwm2 = FileListHWM(value=["some/path", "another.file"], ...) assert hwm1 - "another.file" == hwm2 # same as FileListHWM(value=hwm1.value - "another.file", ...)
- copy(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, update: DictStrAny | None = None, deep: bool = False) Model #
Duplicate a model, optionally choose which fields to include, exclude and change.
- Parameters:
include – fields to include in new model
exclude – fields to exclude from new model, as with values this takes precedence over include
update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data
deep – set to True to make a deep copy of the model
- Returns:
new model instance
- covers(value: str | PathLike) bool #
Return
True
if input value is already covered by HWMExamples
from etl_entities.old_hwm import FileListHWM old_hwm = FileListHWM(value=["some/path.py"], ...) assert old_hwm.covers("some/path.py") # path in HWM assert not old_hwm.covers("another/path.py") # path not in HWM
- classmethod deserialize(inp: dict)#
Return HWM from dict representation
- Returns:
- resultHWM
Deserialized HWM
Examples
from etl_entities.old_hwm import IntHWM assert IntHWM.deserialize( { "value": "1", "type": "int", "column": {"name": ..., "partition": ...}, "source": ..., "process": ..., } ) == IntHWM(value=1, ...) IntHWM.deserialize({"type": "date"}) # raises ValueError
- dict(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) DictStrAny #
Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
- json(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Callable[[Any], Any] | None = None, models_as_dict: bool = True, **dumps_kwargs: Any) str #
Generate a JSON representation of the model, include and exclude arguments as per dict().
encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().
- property name: str#
Name of HWM
- Returns:
- valuestr
Static value
"file_list"
- property qualified_name: str#
Unique name of HWM
- serialize() dict #
Return dict representation of HWM
- Returns:
- resultdict
Serialized HWM
Examples
from etl_entities.old_hwm import IntHWM old_hwm = IntHWM(value=1, ...) assert old_hwm.serialize() == { "value": "1", "type": "int", "column": {"name": ..., "partition": ...}, "source": ..., "process": ..., }
- set_value(value: ValueType) HWM #
Replaces current HWM value with the passed one, and return HWM.
Note
Changes HWM value in place instead of returning new one
- Returns:
- resultHWM
Self
Examples
from etl_entities.old_hwm import IntHWM old_hwm = IntHWM(value=1, ...) old_hwm.set_value(2) assert old_hwm.value == 2
- update(value: str | PathLike | Iterable[str | PathLike])#
Updates current HWM value with some implementation-specific logic, and return HWM.
Note
Changes HWM value in place
- Returns:
- resultFileListHWM
Self
Examples
from etl_entities.old_hwm import FileListHWM old_hwm = FileListHWM(value=["some/existing_path.py"], ...) # new paths are appended old_hwm.update("some/new_path.py") assert old_hwm.value == [ "some/existing_path.py", "some/new_path.py", ] # existing paths do nothing old_hwm.update("some/existing_path.py") assert old_hwm.value == [ "some/existing_path.py", "some/new_path.py", ]