github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-08 12:31:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Implement lazy_load() for EverNoteLoader (#18538)

Browse Source 
Covered by `test_evernote_loader.py`
This commit is contained in:
Christophe Bornet 2024-03-06 02:29:52 +01:00 committed by GitHub
parent d7dd3cd248
commit a6b5d45e31
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 21 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
libs/community/langchain_community/document_loaders/evernote.py
View File

@ -40,33 +40,32 @@ class EverNoteLoader(BaseLoader):
self.file_path = file_path
self.load_single_document = load_single_document
def load(self) -> List[Document]:
"""Load documents from EverNote export file."""
documents = [
Document(
page_content=note["content"],
metadata={
**{
key: value
for key, value in note.items()
if key not in ["content", "content-raw", "resource"]
def _lazy_load(self) -> Iterator[Document]:
for note in self._parse_note_xml(self.file_path):
if note.get("content") is not None:
yield Document(
page_content=note["content"],
metadata={
**{
key: value
for key, value in note.items()
if key not in ["content", "content-raw", "resource"]
},
**{"source": self.file_path},
},
**{"source": self.file_path},
},
)
for note in self._parse_note_xml(self.file_path)
if note.get("content") is not None
]
)
def lazy_load(self) -> Iterator[Document]:
"""Load documents from EverNote export file."""
if not self.load_single_document:
return documents
return [
Document(
page_content="".join([document.page_content for document in documents]),
yield from self._lazy_load()
else:
yield Document(
page_content="".join(
[document.page_content for document in self._lazy_load()]
),
metadata={"source": self.file_path},
)
]
@staticmethod
def _parse_content(content: str) -> str: