github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-27 08:58:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update and rename everynote.py to evernote.py (#1060)

Browse Source 
Updating this base file as well as the .ipynb file of the example on the
website:

https://github.com/hwchase17/langchain/compare/master...akshayvkt:langchain:patch-1

https://langchain.readthedocs.io/en/latest/modules/document_loaders/examples/everynote.html
This commit is contained in:
Akshay 2023-02-15 22:41:42 -08:00 committed by GitHub
parent 34cba2da32
commit d8ed286200
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
langchain/document_loaders/everynote.py → langchain/document_loaders/evernote.py
View File

@ -1,4 +1,4 @@
"""Load documents from Everynote. """Load documents from Evernote.
https://gist.github.com/foxmask/7b29c43a161e001ff04afdb2f181e31c https://gist.github.com/foxmask/7b29c43a161e001ff04afdb2f181e31c
""" """
@ -52,7 +52,7 @@ def _parse_note(note: List) -> dict:
def _parse_note_xml(xml_file: str) -> str: def _parse_note_xml(xml_file: str) -> str:
"""Parse everynote xml.""" """Parse Evernote xml."""
# Without huge_tree set to True, parser may complain about huge text node # Without huge_tree set to True, parser may complain about huge text node
# Try to recover, because there may be " ", which will cause # Try to recover, because there may be " ", which will cause
# "XMLSyntaxError: Entity 'nbsp' not defined" # "XMLSyntaxError: Entity 'nbsp' not defined"
@ -68,15 +68,15 @@ def _parse_note_xml(xml_file: str) -> str:
return result_string return result_string
class EveryNoteLoader(BaseLoader): class EverNoteLoader(BaseLoader):
"""Loader to load in EverNnote files..""" """Loader to load in EverNote files.."""
def __init__(self, file_path: str): def __init__(self, file_path: str):
"""Initialize with file path.""" """Initialize with file path."""
self.file_path = file_path self.file_path = file_path
def load(self) -> List[Document]: def load(self) -> List[Document]:
"""Load document from EveryNote file.""" """Load document from EverNote file."""
text = _parse_note_xml(self.file_path) text = _parse_note_xml(self.file_path)
metadata = {"source": self.file_path} metadata = {"source": self.file_path}
return [Document(page_content=text, metadata=metadata)] return [Document(page_content=text, metadata=metadata)]