Skip to content

armgit / mem0

Public Imported from GitHub
0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

[tests]: add more tests for pdf_file loader (#769)

SerSamgyd2fd3ce434a1
diff --git a/tests/loaders/test_pdf_file.py b/tests/loaders/test_pdf_file.py
new file mode 100644
index 000000000..6e6dda6e5
--- /dev/null
+++ b/tests/loaders/test_pdf_file.py
@@ -0,0 +1,36 @@
+import pytest
+from langchain.schema import Document
+
+
+def test_load_data(loader, mocker):
+ mocked_pypdfloader = mocker.patch("embedchain.loaders.pdf_file.PyPDFLoader")
+ mocked_pypdfloader.return_value.load_and_split.return_value = [
+ Document(page_content="Page 0 Content", metadata={"source": "example.pdf", "page": 0}),
+ Document(page_content="Page 1 Content", metadata={"source": "example.pdf", "page": 1}),
+ ]
+
+ mock_sha256 = mocker.patch("embedchain.loaders.docs_site_loader.hashlib.sha256")
+ doc_id = "mocked_hash"
+ mock_sha256.return_value.hexdigest.return_value = doc_id
+
+ result = loader.load_data("dummy_url")
+ assert result["doc_id"] is doc_id
+ assert result["data"] == [
+ {"content": "Page 0 Content", "meta_data": {"source": "example.pdf", "page": 0, "url": "dummy_url"}},
+ {"content": "Page 1 Content", "meta_data": {"source": "example.pdf", "page": 1, "url": "dummy_url"}},
+ ]
+
+
+def test_load_data_fails_to_find_data(loader, mocker):
+ mocked_pypdfloader = mocker.patch("embedchain.loaders.pdf_file.PyPDFLoader")
+ mocked_pypdfloader.return_value.load_and_split.return_value = []
+
+ with pytest.raises(ValueError):
+ loader.load_data("dummy_url")
+
+
+def loader():
+ from embedchain.loaders.pdf_file import PdfFileLoader
+
+ return PdfFileLoader()