yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-12-12 23:37:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revert "fix: make pypdf converter more robust (#8427)" (#8428)

Browse Source 
This reverts commit d234c75168dcb49866a6714aa232f37d56f72cab.
This commit is contained in:
Silvano Cerza 2024-10-01 11:55:25 +02:00 committed by GitHub
parent d234c75168
commit d6f073f9b3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 2 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
haystack/components/converters/pypdf.py
View File

@ -108,10 +108,8 @@ class PyPDFToDocument:
:returns: :returns:
Deserialized component. Deserialized component.
""" """
# the converter default is `None`, check if it was defined before deserializing converter_class = deserialize_type(data["init_parameters"]["converter"]["type"])
if "converter" in data["init_parameters"]: data["init_parameters"]["converter"] = converter_class.from_dict(data["init_parameters"]["converter"])
converter_class = deserialize_type(data["init_parameters"]["converter"]["type"])
data["init_parameters"]["converter"] = converter_class.from_dict(data["init_parameters"]["converter"])
return default_from_dict(cls, data) return default_from_dict(cls, data)
@component.output_types(documents=List[Document]) @component.output_types(documents=List[Document])

5
releasenotes/notes/pypdf-converter-robust-from-dict-35ebe6aaab944b19.yaml
View File

@ -1,5 +0,0 @@
---
fixes:
- |
Make the `from_dict` method of the `PyPDFToDocument` more robust to cases when the converter is
not provided in the dictionary.

6
test/components/converters/test_pypdf_to_document.py
View File

@ -40,12 +40,6 @@ class TestPyPDFToDocument:
assert isinstance(instance, PyPDFToDocument) assert isinstance(instance, PyPDFToDocument)
assert isinstance(instance.converter, DefaultConverter) assert isinstance(instance.converter, DefaultConverter)
def test_from_dict_no_converter(self):
data = {"type": "haystack.components.converters.pypdf.PyPDFToDocument", "init_parameters": {}}
instance = PyPDFToDocument.from_dict(data)
assert isinstance(instance, PyPDFToDocument)
assert isinstance(instance.converter, DefaultConverter)
@pytest.mark.integration @pytest.mark.integration
def test_run(self, test_files_path, pypdf_converter): def test_run(self, test_files_path, pypdf_converter):
""" """