mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-03 15:11:30 +00:00
f193d3d43b
### Description Building off of PR https://github.com/Unstructured-IO/unstructured/pull/2179, updating fsspec based connectors to use better authentication field handling. This PR adds in the following changes: * Update the base classes to inherit from the enhanced json mixin * Add in a new access config dataclass that should be used as a nest dataclass in the connector configs * Update the code extracting configs out of the cli options dictionary to support the nested access config if it exists on the parent config * Update all fsspec connectors with explicit access configs given what each one's SDKs support * Update the json mixin and enhanced field to support a name override when serializing/deserializing from json/dicts. This allows a different name to be used for the CLI option than what the name of the field is on the dataclass. * Update all the writes to use class-based approach and share the same structure of the runner classes * Above update allowed for better code to be used in the base source and destination CLI commands * Add in utility code around paring a flat dictionary (coming from the click based options) into dataclass-based configs with potentially nested dataclasses. **Slightly unrelated changes:** * session handle removed from pinecone connector as this was breaking the serialization of the write config and didn't have any benefit as a connection was never being shared, the index used simply makes a new http call each time it's invoked. * Dedicated write configs were created for all destination connectors to better support serialization * Refactor of Elasticsearch connector included, with update to ingest test to use auth **TODOs** * Left a `#TODO` in the code but the way session handler is implemented right now, it breaks serialization since it adds a generic variable based on the library being used for a connector (i.e. `googleapiclient.discovery.Resource`) which is not serializable. This will need to be updated to omit that from serialization but still support the current workflow. --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: rbiseck3 <rbiseck3@users.noreply.github.com>
61 lines
1.8 KiB
Python
61 lines
1.8 KiB
Python
import json
|
|
from dataclasses import Field, dataclass, fields
|
|
|
|
import pytest
|
|
|
|
from unstructured.ingest.enhanced_dataclass import EnhancedDataClassJsonMixin, enhanced_field
|
|
from unstructured.ingest.enhanced_dataclass.dataclasses import EnhancedField
|
|
|
|
|
|
@dataclass
|
|
class AuthData(EnhancedDataClassJsonMixin):
|
|
username: str
|
|
password: str = enhanced_field(sensitive=True)
|
|
date: int = enhanced_field(overload_name="time")
|
|
|
|
|
|
auth = AuthData(username="my name", password="top secret", date=3)
|
|
|
|
|
|
def test_enhanced_field():
|
|
fs = fields(AuthData)
|
|
for f in fs:
|
|
if f.name == "username":
|
|
assert isinstance(f, Field)
|
|
assert hasattr(f, "sensitive") is False
|
|
else:
|
|
assert isinstance(f, EnhancedField)
|
|
if f.name == "password":
|
|
assert f.sensitive is True
|
|
else:
|
|
assert not f.sensitive
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("apply_name_overload", "expected_dict"),
|
|
[
|
|
(True, {"username": "my name", "password": "THIS IS REDACTED", "time": 3}),
|
|
(False, {"username": "my name", "password": "THIS IS REDACTED", "date": 3}),
|
|
],
|
|
)
|
|
def test_to_json(apply_name_overload: bool, expected_dict: dict):
|
|
j = auth.to_json(
|
|
redact_sensitive=True,
|
|
redacted_text="THIS IS REDACTED",
|
|
apply_name_overload=apply_name_overload,
|
|
)
|
|
expected = json.dumps(expected_dict)
|
|
assert j == expected
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("apply_name_overload", "expected_dict"),
|
|
[
|
|
(True, {"username": "my name", "password": "***REDACTED***", "time": 3}),
|
|
(False, {"username": "my name", "password": "***REDACTED***", "date": 3}),
|
|
],
|
|
)
|
|
def test_to_dict(apply_name_overload: bool, expected_dict: dict):
|
|
d = auth.to_dict(redact_sensitive=True, apply_name_overload=apply_name_overload)
|
|
assert d == expected_dict
|