vrr/open-notebook
2
0
Fork 0
mirror of https://github.com/lfnovo/open-notebook.git synced 2026-04-29 03:50:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

separate source and content graph

Browse source
This commit is contained in:
LUIS NOVO 2024-11-10 13:30:03 -03:00
parent b42a95b35f
commit 2e2a4947b3
12 changed files with 167 additions and 56 deletions
Download patch file Download diff file Expand all files Collapse all files

4
open_notebook/graphs/content_processing/pdf.py
View file

@ -4,7 +4,7 @@ import unicodedata
import fitz # type: ignore
from loguru import logger
from open_notebook.graphs.content_processing.state import SourceState
from open_notebook.graphs.content_processing.state import ContentState
# todo: find tables - https://pymupdf.readthedocs.io/en/latest/the-basics.html#extracting-tables-from-a-page
# todo: what else can we do to make the text more readable?
@ -127,7 +127,7 @@ def _extract_text_from_pdf(pdf_path):
doc.close()
def extract_pdf(state: SourceState):
def extract_pdf(state: ContentState):
"""
Parse the text file and print its content.
"""