jyapayne/dify
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix document extractor node incorrectly processing doc and ppt files (#12902)

Browse source
This commit is contained in:
AugNSo 2025-02-12 18:04:28 +08:00 • committed by GitHub
commit 2b86465d4c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 59 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

8
api/tests/unit_tests/core/workflow/nodes/test_document_extractor_node.py
View file

@ -8,7 +8,7 @@ from core.variables.variables import StringVariable
from core.workflow.entities.node_entities import NodeRunResult
from core.workflow.nodes.document_extractor import DocumentExtractorNode, DocumentExtractorNodeData
from core.workflow.nodes.document_extractor.node import (
_extract_text_from_doc,
_extract_text_from_docx,
_extract_text_from_pdf,
_extract_text_from_plain_text,
)
@ -120,7 +120,7 @@ def test_run_extract_text(
monkeypatch.setattr("core.workflow.nodes.document_extractor.node._extract_text_from_pdf", mock_pdf_extract)
elif mime_type.startswith("application/vnd.openxmlformats"):
mock_docx_extract = Mock(return_value=expected_text[0])
monkeypatch.setattr("core.workflow.nodes.document_extractor.node._extract_text_from_doc", mock_docx_extract)
monkeypatch.setattr("core.workflow.nodes.document_extractor.node._extract_text_from_docx", mock_docx_extract)
result = document_extractor_node._run()
@ -163,14 +163,14 @@ def test_extract_text_from_pdf(mock_pdf_document):
@patch("docx.Document")
def test_extract_text_from_doc(mock_document):
def test_extract_text_from_docx(mock_document):
mock_paragraph1 = Mock()
mock_paragraph1.text = "Paragraph 1"
mock_paragraph2 = Mock()
mock_paragraph2.text = "Paragraph 2"
mock_document.return_value.paragraphs = [mock_paragraph1, mock_paragraph2]
text = _extract_text_from_doc(b"PK\x03\x04")
text = _extract_text_from_docx(b"PK\x03\x04")
assert text == "Paragraph 1\nParagraph 2"